Publications

• [ 2023 ]
• [ 2022 ]
• [ 2021 ]
• [ 2020 ]
• [ 2019 ]
• [ 2018 ]
• [ 2017 ]
• [ 2016 ]
• [ 2015 ]
• [ 2014 ]
• [ 2013 ]
• [ 2012 ]
• [ 2011 ]
• [ 2010 ]
• [ 2009 ]
• [ 2008 ]
• [ 2007 ]
• [ 2006 ]
• [ 2005 ]
• [ 2004 ]
• [ 2003 ]
• [ 2002 ]
• [ 2001 ]
• [ 2000 ]

• 
  ConvMOS: climate model output statistics with deep learning Steininger, Michael; Abel, Daniel; Ziegler, Katrin; Krause, Anna; Paeth, Heiko; Hotho, Andreas in Data Mining and Knowledge Discovery (2023). 37(1) 136–166.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.

  @article{steininger2023convmos, abstract = {Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.}, author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas}, journal = {Data Mining and Knowledge Discovery}, keywords = {from:annakrause}, number = 1, pages = {136–166}, title = {ConvMOS: climate model output statistics with deep learning}, volume = 37, year = 2023 }

  %0 Journal Article %1 steininger2023convmos %A Steininger, Michael %A Abel, Daniel %A Ziegler, Katrin %A Krause, Anna %A Paeth, Heiko %A Hotho, Andreas %D 2023 %J Data Mining and Knowledge Discovery %N 1 %P 136--166 %R 10.1007/s10618-022-00877-6 %T ConvMOS: climate model output statistics with deep learning %U https://doi.org/10.1007/s10618-022-00877-6 %V 37 %X Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.

• 
  CLIP knows image aesthetics Hentschel, Simon; Kobs, Konstantin; Hotho, Andreas in Frontiers in artificial intelligence (2022). 5 976235.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  Most Image Aesthetic Assessment (IAA) methods use a pretrained ImageNet classification model as a base to fine-tune. We hypothesize that content classification is not an optimal pretraining task for IAA, since the task discourages the extraction of features that are useful for IAA, e.g., composition, lighting, or style. On the other hand, we argue that the Contrastive Language-Image Pretraining (CLIP) model is a better base for IAA models, since it has been trained using natural language supervision. Due to the rich nature of language, CLIP needs to learn a broad range of image features that correlate with sentences describing the image content, composition, environments, and even subjective feelings about the image. While it has been shown that CLIP extracts features useful for content classification tasks, its suitability for tasks that require the extraction of style-based features like IAA has not yet been shown. We test our hypothesis by conducting a three-step study, investigating the usefulness of features extracted by CLIP compared to features obtained from the last layer of a comparable ImageNet classification model. In each step, we get more computationally expensive. First, we engineer natural language prompts that let CLIP assess an image's aesthetic without adjusting any weights in the model. To overcome the challenge that CLIP's prompting only is applicable to classification tasks, we propose a simple but effective strategy to convert multiple prompts to a continuous scalar as required when predicting an image's mean aesthetic score. Second, we train a linear regression on the AVA dataset using image features obtained by CLIP's image encoder. The resulting model outperforms a linear regression trained on features from an ImageNet classification model. It also shows competitive performance with fully fine-tuned networks based on ImageNet, while only training a single layer. Finally, by fine-tuning CLIP's image encoder on the AVA dataset, we show that CLIP only needs a fraction of training epochs to converge, while also performing better than a fine-tuned ImageNet model. Overall, our experiments suggest that CLIP is better suited as a base model for IAA methods than ImageNet pretrained networks.

  @article{PMID:36504688, abstract = {Most Image Aesthetic Assessment (IAA) methods use a pretrained ImageNet classification model as a base to fine-tune. We hypothesize that content classification is not an optimal pretraining task for IAA, since the task discourages the extraction of features that are useful for IAA, e.g., composition, lighting, or style. On the other hand, we argue that the Contrastive Language-Image Pretraining (CLIP) model is a better base for IAA models, since it has been trained using natural language supervision. Due to the rich nature of language, CLIP needs to learn a broad range of image features that correlate with sentences describing the image content, composition, environments, and even subjective feelings about the image. While it has been shown that CLIP extracts features useful for content classification tasks, its suitability for tasks that require the extraction of style-based features like IAA has not yet been shown. We test our hypothesis by conducting a three-step study, investigating the usefulness of features extracted by CLIP compared to features obtained from the last layer of a comparable ImageNet classification model. In each step, we get more computationally expensive. First, we engineer natural language prompts that let CLIP assess an image's aesthetic without adjusting any weights in the model. To overcome the challenge that CLIP's prompting only is applicable to classification tasks, we propose a simple but effective strategy to convert multiple prompts to a continuous scalar as required when predicting an image's mean aesthetic score. Second, we train a linear regression on the AVA dataset using image features obtained by CLIP's image encoder. The resulting model outperforms a linear regression trained on features from an ImageNet classification model. It also shows competitive performance with fully fine-tuned networks based on ImageNet, while only training a single layer. Finally, by fine-tuning CLIP's image encoder on the AVA dataset, we show that CLIP only needs a fraction of training epochs to converge, while also performing better than a fine-tuned ImageNet model. Overall, our experiments suggest that CLIP is better suited as a base model for IAA methods than ImageNet pretrained networks.}, author = {Hentschel, Simon and Kobs, Konstantin and Hotho, Andreas}, journal = {Frontiers in artificial intelligence}, keywords = {from:hotho}, pages = 976235, title = {CLIP knows image aesthetics}, volume = 5, year = 2022 }

  %0 Journal Article %1 PMID:36504688 %A Hentschel, Simon %A Kobs, Konstantin %A Hotho, Andreas %D 2022 %J Frontiers in artificial intelligence %P 976235 %R 10.3389/frai.2022.976235 %T CLIP knows image aesthetics %U https://europepmc.org/articles/PMC9732445 %V 5 %X Most Image Aesthetic Assessment (IAA) methods use a pretrained ImageNet classification model as a base to fine-tune. We hypothesize that content classification is not an optimal pretraining task for IAA, since the task discourages the extraction of features that are useful for IAA, e.g., composition, lighting, or style. On the other hand, we argue that the Contrastive Language-Image Pretraining (CLIP) model is a better base for IAA models, since it has been trained using natural language supervision. Due to the rich nature of language, CLIP needs to learn a broad range of image features that correlate with sentences describing the image content, composition, environments, and even subjective feelings about the image. While it has been shown that CLIP extracts features useful for content classification tasks, its suitability for tasks that require the extraction of style-based features like IAA has not yet been shown. We test our hypothesis by conducting a three-step study, investigating the usefulness of features extracted by CLIP compared to features obtained from the last layer of a comparable ImageNet classification model. In each step, we get more computationally expensive. First, we engineer natural language prompts that let CLIP assess an image's aesthetic without adjusting any weights in the model. To overcome the challenge that CLIP's prompting only is applicable to classification tasks, we propose a simple but effective strategy to convert multiple prompts to a continuous scalar as required when predicting an image's mean aesthetic score. Second, we train a linear regression on the AVA dataset using image features obtained by CLIP's image encoder. The resulting model outperforms a linear regression trained on features from an ImageNet classification model. It also shows competitive performance with fully fine-tuned networks based on ImageNet, while only training a single layer. Finally, by fine-tuning CLIP's image encoder on the AVA dataset, we show that CLIP only needs a fraction of training epochs to converge, while also performing better than a fine-tuned ImageNet model. Overall, our experiments suggest that CLIP is better suited as a base model for IAA methods than ImageNet pretrained networks.
• 
  Towards Responsible Medical Diagnostics Recommendation Systems Schl{\"{o}}r, Daniel; Hotho, Andreas in CoRR (2022). abs/2209.03760
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{DBLP:journals/corr/abs-2209-03760, author = {Schl{\"{o}}r, Daniel and Hotho, Andreas}, journal = {CoRR}, keywords = {from:hotho}, title = {Towards Responsible Medical Diagnostics Recommendation Systems}, volume = {abs/2209.03760}, year = 2022 }

  %0 Journal Article %1 DBLP:journals/corr/abs-2209-03760 %A Schl{\"{o}}r, Daniel %A Hotho, Andreas %D 2022 %J CoRR %R 10.48550/arXiv.2209.03760 %T Towards Responsible Medical Diagnostics Recommendation Systems %U https://doi.org/10.48550/arXiv.2209.03760 %V abs/2209.03760
• 
  On Learning Hierarchical Embeddings from Encrypted Network Traffic Wehner, Nikolas; Ring, Markus; Sch{\"{u}}ler, Joshua; Hotho, Andreas; Ho{\ss}feld, Tobias; Seufert, Michael in 2022 {IEEE/IFIP} Network Operations and Management Symposium, {NOMS} 2022, Budapest, Hungary, April 25-29, 2022 (2022). 1–7.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @inproceedings{DBLP:conf/noms/WehnerRSHHS22, author = {Wehner, Nikolas and Ring, Markus and Sch{\"{u}}ler, Joshua and Hotho, Andreas and Ho{\ss}feld, Tobias and Seufert, Michael}, booktitle = {2022 {IEEE/IFIP} Network Operations and Management Symposium, {NOMS} 2022, Budapest, Hungary, April 25-29, 2022}, keywords = {from:hotho}, pages = {1–7}, publisher = {{IEEE}}, title = {On Learning Hierarchical Embeddings from Encrypted Network Traffic}, year = 2022 }

  %0 Conference Paper %1 DBLP:conf/noms/WehnerRSHHS22 %A Wehner, Nikolas %A Ring, Markus %A Sch{\"{u}}ler, Joshua %A Hotho, Andreas %A Ho{\ss}feld, Tobias %A Seufert, Michael %B 2022 {IEEE/IFIP} Network Operations and Management Symposium, {NOMS} 2022, Budapest, Hungary, April 25-29, 2022 %D 2022 %I {IEEE} %P 1--7 %R 10.1109/NOMS54207.2022.9789896 %T On Learning Hierarchical Embeddings from Encrypted Network Traffic %U https://doi.org/10.1109/NOMS54207.2022.9789896
• 
  The Impact of Different System Call Representations on Intrusion Detection Wunderlich, Sarah; Ring, Markus; Landes, Dieter; Hotho, Andreas in Log. J. {IGPL} (2022). 30(2) 239–251.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{DBLP:journals/igpl/WunderlichRLH22, author = {Wunderlich, Sarah and Ring, Markus and Landes, Dieter and Hotho, Andreas}, journal = {Log. J. {IGPL}}, keywords = {from:hotho}, number = 2, pages = {239–251}, title = {The Impact of Different System Call Representations on Intrusion Detection}, volume = 30, year = 2022 }

  %0 Journal Article %1 DBLP:journals/igpl/WunderlichRLH22 %A Wunderlich, Sarah %A Ring, Markus %A Landes, Dieter %A Hotho, Andreas %D 2022 %J Log. J. {IGPL} %N 2 %P 239--251 %R 10.1093/jigpal/jzaa058 %T The Impact of Different System Call Representations on Intrusion Detection %U https://doi.org/10.1093/jigpal/jzaa058 %V 30
• 
  Do Different Deep Metric Learning Losses Lead to Similar Learned Features? Kobs, Konstantin; Steininger, Michael; Dulny, Andrzej; Hotho, Andreas in CoRR (2022). abs/2205.02698
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{DBLP:journals/corr/abs-2205-02698, author = {Kobs, Konstantin and Steininger, Michael and Dulny, Andrzej and Hotho, Andreas}, journal = {CoRR}, keywords = {from:hotho}, title = {Do Different Deep Metric Learning Losses Lead to Similar Learned Features?}, volume = {abs/2205.02698}, year = 2022 }

  %0 Journal Article %1 DBLP:journals/corr/abs-2205-02698 %A Kobs, Konstantin %A Steininger, Michael %A Dulny, Andrzej %A Hotho, Andreas %D 2022 %J CoRR %R 10.48550/arXiv.2205.02698 %T Do Different Deep Metric Learning Losses Lead to Similar Learned Features? %U https://doi.org/10.48550/arXiv.2205.02698 %V abs/2205.02698
• 
  Sequential Item Recommendation in the {MOBA} Game Dota 2 Dallmann, Alexander; Kohlmann, Johannes; Zoller, Daniel; Hotho, Andreas in CoRR (2022). abs/2201.08724
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{DBLP:journals/corr/abs-2201-08724, author = {Dallmann, Alexander and Kohlmann, Johannes and Zoller, Daniel and Hotho, Andreas}, journal = {CoRR}, keywords = {from:hotho}, title = {Sequential Item Recommendation in the {MOBA} Game Dota 2}, volume = {abs/2201.08724}, year = 2022 }

  %0 Journal Article %1 DBLP:journals/corr/abs-2201-08724 %A Dallmann, Alexander %A Kohlmann, Johannes %A Zoller, Daniel %A Hotho, Andreas %D 2022 %J CoRR %R 10.48550/arXiv.2201.08724 %T Sequential Item Recommendation in the {MOBA} Game Dota 2 %U https://arxiv.org/abs/2201.08724 %V abs/2201.08724
• 
  SenPoi at SemEval-2022 Task 10: Point me to your Opinion, SenPoi Pfister, Jan; Wankerl, Sebastian; Hotho, Andreas in Proceedings of the 16th International Workshop on Semantic Evaluation, SemEval@NAACL 2022, Seattle, Washington, United States, July 14-15, 2022, G. Emerson, N. Schluter, G. Stanovsky, R. Kumar, A. Palmer, N. Schneider, S. Singh, S. Ratan (eds.) (2022). 1313–1323.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @inproceedings{DBLP:conf/semeval/PfisterWH22, author = {Pfister, Jan and Wankerl, Sebastian and Hotho, Andreas}, booktitle = {Proceedings of the 16th International Workshop on Semantic Evaluation, SemEval@NAACL 2022, Seattle, Washington, United States, July 14-15, 2022}, editor = {Emerson, Guy and Schluter, Natalie and Stanovsky, Gabriel and Kumar, Ritesh and Palmer, Alexis and Schneider, Nathan and Singh, Siddharth and Ratan, Shyam}, keywords = {from:hotho}, pages = {1313–1323}, publisher = {Association for Computational Linguistics}, title = {SenPoi at SemEval-2022 Task 10: Point me to your Opinion, SenPoi}, year = 2022 }

  %0 Conference Paper %1 DBLP:conf/semeval/PfisterWH22 %A Pfister, Jan %A Wankerl, Sebastian %A Hotho, Andreas %B Proceedings of the 16th International Workshop on Semantic Evaluation, SemEval@NAACL 2022, Seattle, Washington, United States, July 14-15, 2022 %D 2022 %E Emerson, Guy %E Schluter, Natalie %E Stanovsky, Gabriel %E Kumar, Ritesh %E Palmer, Alexis %E Schneider, Nathan %E Singh, Siddharth %E Ratan, Shyam %I Association for Computational Linguistics %P 1313--1323 %R 10.18653/v1/2022.semeval-1.183 %T SenPoi at SemEval-2022 Task 10: Point me to your Opinion, SenPoi %U https://doi.org/10.18653/v1/2022.semeval-1.183
• 
  NeuralPDE: Modelling Dynamical Systems from Data Dulny, Andrzej; Hotho, Andreas; Krause, Anna in {KI} 2022: Advances in Artificial Intelligence - 45th German Conference on AI, Trier, Germany, September 19-23, 2022, Proceedings, Lecture Notes in Computer Science, R. Bergmann, L. Malburg, S. C. Rodermund, I. J. Timm (eds.) (2022). (Vol. 13404) 75–89.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @inproceedings{DBLP:conf/ki/DulnyHK22, author = {Dulny, Andrzej and Hotho, Andreas and Krause, Anna}, booktitle = {{KI} 2022: Advances in Artificial Intelligence - 45th German Conference on AI, Trier, Germany, September 19-23, 2022, Proceedings}, editor = {Bergmann, Ralph and Malburg, Lukas and Rodermund, Stephanie C. and Timm, Ingo J.}, keywords = {from:hotho}, pages = {75–89}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {NeuralPDE: Modelling Dynamical Systems from Data}, volume = 13404, year = 2022 }

  %0 Conference Paper %1 DBLP:conf/ki/DulnyHK22 %A Dulny, Andrzej %A Hotho, Andreas %A Krause, Anna %B {KI} 2022: Advances in Artificial Intelligence - 45th German Conference on AI, Trier, Germany, September 19-23, 2022, Proceedings %D 2022 %E Bergmann, Ralph %E Malburg, Lukas %E Rodermund, Stephanie C. %E Timm, Ingo J. %I Springer %P 75--89 %R 10.1007/978-3-031-15791-2\_8 %T NeuralPDE: Modelling Dynamical Systems from Data %U https://doi.org/10.1007/978-3-031-15791-2 %V 13404
• 
  Comparison of Data Representations and Machine Learning Architectures for User Identification on Arbitrary Motion Sequences Schell, Christian; Hotho, Andreas; Latoschik, Marc Erich in CoRR (2022). abs/2210.00527
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{DBLP:journals/corr/abs-2210-00527, author = {Schell, Christian and Hotho, Andreas and Latoschik, Marc Erich}, journal = {CoRR}, keywords = {from:hotho}, title = {Comparison of Data Representations and Machine Learning Architectures for User Identification on Arbitrary Motion Sequences}, volume = {abs/2210.00527}, year = 2022 }

  %0 Journal Article %1 DBLP:journals/corr/abs-2210-00527 %A Schell, Christian %A Hotho, Andreas %A Latoschik, Marc Erich %D 2022 %J CoRR %R 10.48550/arXiv.2210.00527 %T Comparison of Data Representations and Machine Learning Architectures for User Identification on Arbitrary Motion Sequences %U https://doi.org/10.48550/arXiv.2210.00527 %V abs/2210.00527
• 
  Towards Responsible Medical Diagnostics Recommendation Systems Schlör, Daniel; Hotho, Andreas (2022).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  The early development and deployment of hospital and healthcare information systems have encouraged the ongoing digitization of processes in hospitals. Many of these processes, which previously required paperwork and telephone arrangements, are now integrated into IT solutions and require physicians and medical staff to interact with appropriate interfaces and tools. Although this shift to digital data management and process support has benefited patient care in many ways, it requires physicians to accurately capture all relevant information digitally for billing and documentation purposes, which takes a lot of time away from actual patient care work. However, systematic collection of healthcare data over a long period of time offers opportunities to improve this process and support medical staff by introducing recommender systems. Based on a practical working example, in this position paper, we will outline the design of a responsible recommender system in the medical context from a technical, application driven perspective and discuss potential design choices and criteria with a specific focus on accountability, safety, and fairness.

  @misc{schlor2022towards, abstract = {The early development and deployment of hospital and healthcare information systems have encouraged the ongoing digitization of processes in hospitals. Many of these processes, which previously required paperwork and telephone arrangements, are now integrated into IT solutions and require physicians and medical staff to interact with appropriate interfaces and tools. Although this shift to digital data management and process support has benefited patient care in many ways, it requires physicians to accurately capture all relevant information digitally for billing and documentation purposes, which takes a lot of time away from actual patient care work. However, systematic collection of healthcare data over a long period of time offers opportunities to improve this process and support medical staff by introducing recommender systems. Based on a practical working example, in this position paper, we will outline the design of a responsible recommender system in the medical context from a technical, application driven perspective and discuss potential design choices and criteria with a specific focus on accountability, safety, and fairness.}, author = {Schlör, Daniel and Hotho, Andreas}, keywords = {from:daschloer}, note = {cite arxiv:2209.03760Comment: 4th FAccTRec Workshop on Responsible Recommendation}, title = {Towards Responsible Medical Diagnostics Recommendation Systems}, year = 2022 }

  %0 Generic %1 schlor2022towards %A Schlör, Daniel %A Hotho, Andreas %D 2022 %T Towards Responsible Medical Diagnostics Recommendation Systems %U http://arxiv.org/abs/2209.03760 %X The early development and deployment of hospital and healthcare information systems have encouraged the ongoing digitization of processes in hospitals. Many of these processes, which previously required paperwork and telephone arrangements, are now integrated into IT solutions and require physicians and medical staff to interact with appropriate interfaces and tools. Although this shift to digital data management and process support has benefited patient care in many ways, it requires physicians to accurately capture all relevant information digitally for billing and documentation purposes, which takes a lot of time away from actual patient care work. However, systematic collection of healthcare data over a long period of time offers opportunities to improve this process and support medical staff by introducing recommender systems. Based on a practical working example, in this position paper, we will outline the design of a responsible recommender system in the medical context from a technical, application driven perspective and discuss potential design choices and criteria with a specific focus on accountability, safety, and fairness.
• 
  ConvMOS: Climate Model Output Statistics with Deep Learning Steininger, Michael; Abel, Daniel; Ziegler, Katrin; Krause, Anna; Paeth, Heiko; Hotho, Andreas in Data Mining and Knowledge Discovery, (P. Cellier; K. Dembczynski; A. Zimmermann; E. Devijver, eds.) (2022).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.

  @article{steininger2022convmos, abstract = {Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.}, author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas}, editor = {Cellier, Peggy and Dembczynski, Krzysztof and Zimmermann, Albrecht and Devijver, Emilie}, journal = {Data Mining and Knowledge Discovery}, keywords = {from:msteininger}, month = {October}, publisher = {Springer}, title = {ConvMOS: Climate Model Output Statistics with Deep Learning}, year = 2022 }

  %0 Journal Article %1 steininger2022convmos %A Steininger, Michael %A Abel, Daniel %A Ziegler, Katrin %A Krause, Anna %A Paeth, Heiko %A Hotho, Andreas %D 2022 %E Cellier, Peggy %E Dembczynski, Krzysztof %E Zimmermann, Albrecht %E Devijver, Emilie %I Springer %J Data Mining and Knowledge Discovery %R 10.1007/s10618-022-00877-6 %T ConvMOS: Climate Model Output Statistics with Deep Learning %X Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts. %@ 1573-756X
• 
  On Background Bias in Deep Metric Learning Kobs, Konstantin; Hotho, Andreas in CoRR (2022). abs/2210.01615
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{DBLP:journals/corr/abs-2210-01615, author = {Kobs, Konstantin and Hotho, Andreas}, journal = {CoRR}, keywords = {from:hotho}, title = {On Background Bias in Deep Metric Learning}, volume = {abs/2210.01615}, year = 2022 }

  %0 Journal Article %1 DBLP:journals/corr/abs-2210-01615 %A Kobs, Konstantin %A Hotho, Andreas %D 2022 %J CoRR %R 10.48550/arXiv.2210.01615 %T On Background Bias in Deep Metric Learning %U https://doi.org/10.48550/arXiv.2210.01615 %V abs/2210.01615
• 
  One Graph to Rule them All: Using {NLP} and Graph Neural Networks to analyse Tolkien’s Legendarium Perri, Vincenzo; Qarkaxhija, Lisi; Zehe, Albin; Hotho, Andreas; Scholtes, Ingo in Proceedings of the Computational Humanities Research Conference 2022, {CHR} 2022, Antwerp, Belgium, December 12-14, 2022, {CEUR} Workshop Proceedings, F. Karsdorp, K. L. Nielbo (eds.) (2022). (Vol. 3290) 291–317.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{perri2022graph, author = {Perri, Vincenzo and Qarkaxhija, Lisi and Zehe, Albin and Hotho, Andreas and Scholtes, Ingo}, booktitle = {Proceedings of the Computational Humanities Research Conference 2022, {CHR} 2022, Antwerp, Belgium, December 12-14, 2022}, editor = {Karsdorp, Folgert and Nielbo, Kristoffer L.}, keywords = {from:albinzehe}, pages = {291–317}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {One Graph to Rule them All: Using {NLP} and Graph Neural Networks to analyse Tolkien's Legendarium}, volume = 3290, year = 2022 }

  %0 Conference Paper %1 perri2022graph %A Perri, Vincenzo %A Qarkaxhija, Lisi %A Zehe, Albin %A Hotho, Andreas %A Scholtes, Ingo %B Proceedings of the Computational Humanities Research Conference 2022, {CHR} 2022, Antwerp, Belgium, December 12-14, 2022 %D 2022 %E Karsdorp, Folgert %E Nielbo, Kristoffer L. %I CEUR-WS.org %P 291--317 %T One Graph to Rule them All: Using {NLP} and Graph Neural Networks to analyse Tolkien's Legendarium %U http://ceur-ws.org/Vol-3290/long\_paper2171.pdf %V 3290
• 
  InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images Kobs, Konstantin; Steininger, Michael; Hotho, Andreas (2022).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Common Deep Metric Learning (DML) datasets specify only one notion of similarity, e.g., two images in the Cars196 dataset are deemed similar if they show the same car model. We argue that depending on the application, users of image retrieval systems have different and changing similarity notions that should be incorporated as easily as possible. Therefore, we present Language-Guided Zero-Shot Deep Metric Learning (LanZ-DML) as a new DML setting in which users control the properties that should be important for image representations without training data by only using natural language. To this end, we propose InDiReCT (Image representations using Dimensionality Reduction on CLIP embedded Texts), a model for LanZ-DML on images that exclusively uses a few text prompts for training. InDiReCT utilizes CLIP as a fixed feature extractor for images and texts and transfers the variation in text prompt embeddings to the image embedding space. Extensive experiments on five datasets and overall thirteen similarity notions show that, despite not seeing any images during training, InDiReCT performs better than strong baselines and approaches the performance of fully-supervised models. An analysis reveals that InDiReCT learns to focus on regions of the image that correlate with the desired similarity notion, which makes it a fast to train and easy to use method to create custom embedding spaces only using natural language.

  @misc{kobs2022indirect, abstract = {Common Deep Metric Learning (DML) datasets specify only one notion of similarity, e.g., two images in the Cars196 dataset are deemed similar if they show the same car model. We argue that depending on the application, users of image retrieval systems have different and changing similarity notions that should be incorporated as easily as possible. Therefore, we present Language-Guided Zero-Shot Deep Metric Learning (LanZ-DML) as a new DML setting in which users control the properties that should be important for image representations without training data by only using natural language. To this end, we propose InDiReCT (Image representations using Dimensionality Reduction on CLIP embedded Texts), a model for LanZ-DML on images that exclusively uses a few text prompts for training. InDiReCT utilizes CLIP as a fixed feature extractor for images and texts and transfers the variation in text prompt embeddings to the image embedding space. Extensive experiments on five datasets and overall thirteen similarity notions show that, despite not seeing any images during training, InDiReCT performs better than strong baselines and approaches the performance of fully-supervised models. An analysis reveals that InDiReCT learns to focus on regions of the image that correlate with the desired similarity notion, which makes it a fast to train and easy to use method to create custom embedding spaces only using natural language.}, author = {Kobs, Konstantin and Steininger, Michael and Hotho, Andreas}, keywords = {from:hotho}, note = {cite arxiv:2211.12760Comment: Accepted to WACV 2023}, title = {InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images}, year = 2022 }

  %0 Generic %1 kobs2022indirect %A Kobs, Konstantin %A Steininger, Michael %A Hotho, Andreas %D 2022 %T InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images %U http://arxiv.org/abs/2211.12760 %X Common Deep Metric Learning (DML) datasets specify only one notion of similarity, e.g., two images in the Cars196 dataset are deemed similar if they show the same car model. We argue that depending on the application, users of image retrieval systems have different and changing similarity notions that should be incorporated as easily as possible. Therefore, we present Language-Guided Zero-Shot Deep Metric Learning (LanZ-DML) as a new DML setting in which users control the properties that should be important for image representations without training data by only using natural language. To this end, we propose InDiReCT (Image representations using Dimensionality Reduction on CLIP embedded Texts), a model for LanZ-DML on images that exclusively uses a few text prompts for training. InDiReCT utilizes CLIP as a fixed feature extractor for images and texts and transfers the variation in text prompt embeddings to the image embedding space. Extensive experiments on five datasets and overall thirteen similarity notions show that, despite not seeing any images during training, InDiReCT performs better than strong baselines and approaches the performance of fully-supervised models. An analysis reveals that InDiReCT learns to focus on regions of the image that correlate with the desired similarity notion, which makes it a fast to train and easy to use method to create custom embedding spaces only using natural language.
• 
  Personalization through User Attributes for Transformer-based Sequential Recommendation Fischer, Elisabeth; Dallmann, Alexander; Hotho, Andreas (2022).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{fischer2022personalization, author = {Fischer, Elisabeth and Dallmann, Alexander and Hotho, Andreas}, keywords = {from:e.fischer}, title = {Personalization through User Attributes for Transformer-based Sequential Recommendation}, year = 2022 }

  %0 Journal Article %1 fischer2022personalization %A Fischer, Elisabeth %A Dallmann, Alexander %A Hotho, Andreas %D 2022 %T Personalization through User Attributes for Transformer-based Sequential Recommendation
• 
  Anomaly Detection in Beehives: An Algorithm Comparison Davidson, Padraig; Steininger, Michael; Lautenschlager, Florian; Krause, Anna; Hotho, Andreas in Sensor Networks, A. Ahrens, R. V. Prasad, C. Benavente-Peces, N. Ansari (eds.) (2022). 1–20.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Sensor-equipped beehives allow monitoring the living conditions of bees. Machine learning models can use the data of such hives to learn behavioral patterns and find anomalous events. One type of event that is of particular interest to apiarists for economical reasons is bee swarming. Other events of interest are behavioral anomalies from illness and technical anomalies, e.g. sensor failure. Beekeepers can be supported by suitable machine learning models which can detect these events.

  @inproceedings{10.1007/978-3-031-17718-7_1, abstract = {Sensor-equipped beehives allow monitoring the living conditions of bees. Machine learning models can use the data of such hives to learn behavioral patterns and find anomalous events. One type of event that is of particular interest to apiarists for economical reasons is bee swarming. Other events of interest are behavioral anomalies from illness and technical anomalies, e.g. sensor failure. Beekeepers can be supported by suitable machine learning models which can detect these events.}, address = {Cham}, author = {Davidson, Padraig and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas}, booktitle = {Sensor Networks}, editor = {Ahrens, Andreas and Prasad, RangaRao Venkatesha and Benavente-Peces, C{\'e}sar and Ansari, Nirwan}, keywords = {from:annakrause}, pages = {1–20}, publisher = {Springer International Publishing}, title = {Anomaly Detection in Beehives: An Algorithm Comparison}, year = 2022 }

  %0 Conference Paper %1 10.1007/978-3-031-17718-7_1 %A Davidson, Padraig %A Steininger, Michael %A Lautenschlager, Florian %A Krause, Anna %A Hotho, Andreas %B Sensor Networks %C Cham %D 2022 %E Ahrens, Andreas %E Prasad, RangaRao Venkatesha %E Benavente-Peces, C{\'e}sar %E Ansari, Nirwan %I Springer International Publishing %P 1--20 %T Anomaly Detection in Beehives: An Algorithm Comparison %X Sensor-equipped beehives allow monitoring the living conditions of bees. Machine learning models can use the data of such hives to learn behavioral patterns and find anomalous events. One type of event that is of particular interest to apiarists for economical reasons is bee swarming. Other events of interest are behavioral anomalies from illness and technical anomalies, e.g. sensor failure. Beekeepers can be supported by suitable machine learning models which can detect these events. %@ 978-3-031-17718-7
• 
  {LSX} team5 at {S}em{E}val-2022 Task 8: Multilingual News Article Similarity Assessment based on Word- and Sentence Mover{’}s Distance Heil, Stefan; Kopp, Karina; Zehe, Albin; Kobs, Konstantin; Hotho, Andreas in Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) (2022). 1190–1195.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  This paper introduces our submission for the SemEval 2022 Task 8: Multilingual News Article Similarity. The task of the competition consisted of the development of a model, capable of determining the similarity between pairs of multilingual news articles. To address this challenge, we evaluated the Word Mover{'}s Distance in conjunction with word embeddings from ConceptNet Numberbatch and term frequencies of WorldLex, as well the Sentence Mover{'}s Distance based on sentence embeddings generated by pretrained transformer models of Sentence-BERT. To facilitate the comparison of multilingual articles with Sentence-BERT models, we deployed a Neural Machine Translation system. All our models achieve stable results in multilingual similarity estimation without learning parameters.

  @inproceedings{heil2022lsxteam5, abstract = {This paper introduces our submission for the SemEval 2022 Task 8: Multilingual News Article Similarity. The task of the competition consisted of the development of a model, capable of determining the similarity between pairs of multilingual news articles. To address this challenge, we evaluated the Word Mover{'}s Distance in conjunction with word embeddings from ConceptNet Numberbatch and term frequencies of WorldLex, as well the Sentence Mover{'}s Distance based on sentence embeddings generated by pretrained transformer models of Sentence-BERT. To facilitate the comparison of multilingual articles with Sentence-BERT models, we deployed a Neural Machine Translation system. All our models achieve stable results in multilingual similarity estimation without learning parameters.}, address = {Seattle, United States}, author = {Heil, Stefan and Kopp, Karina and Zehe, Albin and Kobs, Konstantin and Hotho, Andreas}, booktitle = {Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)}, keywords = {from:albinzehe}, month = {jul}, pages = {1190–1195}, publisher = {Association for Computational Linguistics}, title = {{LSX} team5 at {S}em{E}val-2022 Task 8: Multilingual News Article Similarity Assessment based on Word- and Sentence Mover{'}s Distance}, year = 2022 }

  %0 Conference Paper %1 heil2022lsxteam5 %A Heil, Stefan %A Kopp, Karina %A Zehe, Albin %A Kobs, Konstantin %A Hotho, Andreas %B Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) %C Seattle, United States %D 2022 %I Association for Computational Linguistics %P 1190--1195 %T {LSX} team5 at {S}em{E}val-2022 Task 8: Multilingual News Article Similarity Assessment based on Word- and Sentence Mover{'}s Distance %U https://aclanthology.org/2022.semeval-1.168 %X This paper introduces our submission for the SemEval 2022 Task 8: Multilingual News Article Similarity. The task of the competition consisted of the development of a model, capable of determining the similarity between pairs of multilingual news articles. To address this challenge, we evaluated the Word Mover{'}s Distance in conjunction with word embeddings from ConceptNet Numberbatch and term frequencies of WorldLex, as well the Sentence Mover{'}s Distance based on sentence embeddings generated by pretrained transformer models of Sentence-BERT. To facilitate the comparison of multilingual articles with Sentence-BERT models, we deployed a Neural Machine Translation system. All our models achieve stable results in multilingual similarity estimation without learning parameters.
• 
  {W}ue{D}evils at {S}em{E}val-2022 Task 8: Multilingual News Article Similarity via Pair-Wise Sentence Similarity Matrices Wangsadirdja, Dirk; Heinickel, Felix; Trapp, Simon; Zehe, Albin; Kobs, Konstantin; Hotho, Andreas in Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) (2022). 1235–1243.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  We present a system that creates pair-wise cosine and arccosine sentence similarity matrices using multilingual sentence embeddings obtained from pre-trained SBERT and Universal Sentence Encoder (USE) models respectively. For each news article sentence, it searches the most similar sentence from the other article and computes an average score. Further, a convolutional neural network calculates a total similarity score for the article pairs on these matrices. Finally, a random forest regressor merges the previous results to a final score that can optionally be extended with a publishing date score.

  @inproceedings{wangsadirdja2022wuedevils, abstract = {We present a system that creates pair-wise cosine and arccosine sentence similarity matrices using multilingual sentence embeddings obtained from pre-trained SBERT and Universal Sentence Encoder (USE) models respectively. For each news article sentence, it searches the most similar sentence from the other article and computes an average score. Further, a convolutional neural network calculates a total similarity score for the article pairs on these matrices. Finally, a random forest regressor merges the previous results to a final score that can optionally be extended with a publishing date score.}, address = {Seattle, United States}, author = {Wangsadirdja, Dirk and Heinickel, Felix and Trapp, Simon and Zehe, Albin and Kobs, Konstantin and Hotho, Andreas}, booktitle = {Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)}, keywords = {from:albinzehe}, month = {jul}, pages = {1235–1243}, publisher = {Association for Computational Linguistics}, title = {{W}ue{D}evils at {S}em{E}val-2022 Task 8: Multilingual News Article Similarity via Pair-Wise Sentence Similarity Matrices}, year = 2022 }

  %0 Conference Paper %1 wangsadirdja2022wuedevils %A Wangsadirdja, Dirk %A Heinickel, Felix %A Trapp, Simon %A Zehe, Albin %A Kobs, Konstantin %A Hotho, Andreas %B Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) %C Seattle, United States %D 2022 %I Association for Computational Linguistics %P 1235--1243 %T {W}ue{D}evils at {S}em{E}val-2022 Task 8: Multilingual News Article Similarity via Pair-Wise Sentence Similarity Matrices %U https://aclanthology.org/2022.semeval-1.175 %X We present a system that creates pair-wise cosine and arccosine sentence similarity matrices using multilingual sentence embeddings obtained from pre-trained SBERT and Universal Sentence Encoder (USE) models respectively. For each news article sentence, it searches the most similar sentence from the other article and computes an average score. Further, a convolutional neural network calculates a total similarity score for the article pairs on these matrices. Finally, a random forest regressor merges the previous results to a final score that can optionally be extended with a publishing date score.
• 
  Point me to your Opinion, {S}en{P}oi Pfister, Jan; Wankerl, Sebastian; Hotho, Andreas in Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) (2022). 1313–1323.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Structured Sentiment Analysis is the task of extracting sentiment tuples in a graph structure commonly from review texts. We adapt the Aspect-Based Sentiment Analysis pointer network BARTABSA to model this tuple extraction as a sequence prediction task and extend their output grammar to account for the increased complexity of Structured Sentiment Analysis. To predict structured sentiment tuples in languages other than English we swap BART for a multilingual mT5 and introduce a novel Output Length Regularization to mitigate overfitting to common target sequence lengths, thereby improving the performance of the model by up to 70{\%}. We evaluate our approach on seven datasets in five languages including a zero shot crosslingual setting.

  @inproceedings{pfister-etal-2022-senpoi, abstract = {Structured Sentiment Analysis is the task of extracting sentiment tuples in a graph structure commonly from review texts. We adapt the Aspect-Based Sentiment Analysis pointer network BARTABSA to model this tuple extraction as a sequence prediction task and extend their output grammar to account for the increased complexity of Structured Sentiment Analysis. To predict structured sentiment tuples in languages other than English we swap BART for a multilingual mT5 and introduce a novel Output Length Regularization to mitigate overfitting to common target sequence lengths, thereby improving the performance of the model by up to 70{\%}. We evaluate our approach on seven datasets in five languages including a zero shot crosslingual setting.}, address = {Seattle, United States}, author = {Pfister, Jan and Wankerl, Sebastian and Hotho, Andreas}, booktitle = {Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)}, keywords = {from:janpf}, month = {jul}, pages = {1313–1323}, publisher = {Association for Computational Linguistics}, title = {Point me to your Opinion, {S}en{P}oi}, year = 2022 }

  %0 Conference Paper %1 pfister-etal-2022-senpoi %A Pfister, Jan %A Wankerl, Sebastian %A Hotho, Andreas %B Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) %C Seattle, United States %D 2022 %I Association for Computational Linguistics %P 1313--1323 %T Point me to your Opinion, {S}en{P}oi %U https://aclanthology.org/2022.semeval-1.183 %X Structured Sentiment Analysis is the task of extracting sentiment tuples in a graph structure commonly from review texts. We adapt the Aspect-Based Sentiment Analysis pointer network BARTABSA to model this tuple extraction as a sequence prediction task and extend their output grammar to account for the increased complexity of Structured Sentiment Analysis. To predict structured sentiment tuples in languages other than English we swap BART for a multilingual mT5 and introduce a novel Output Length Regularization to mitigate overfitting to common target sequence lengths, thereby improving the performance of the model by up to 70{\%}. We evaluate our approach on seven datasets in five languages including a zero shot crosslingual setting.
• 
  Semi-unsupervised Learning for Time Series Classification Davidson, Padraig; Steininger, Michael; Huhn, André; Krause, Anna; Hotho, Andreas in Milets@KDD (2022).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Time series are ubiquitous and therefore inherently hard to analyze and ultimately to label or cluster. With the rise of the Internet of Things (IoT) and its smart devices, data is collected in large amounts any given second. The collected data is rich in information, as one can detect accidents (e.g. cars) in real time, or assess injury/sickness over a given time span (e.g. health devices). Due to its chaotic nature and massive amounts of datapoints, timeseries are hard to label manually. Furthermore new classes within the data could emerge over time (contrary to e.g. handwritten digits), which would require relabeling the data. In this paper we present SuSL4TS, a deep generative Gaussian mixture model for semi-unsupervised learning, to classify time series data. With our approach we can alleviate manual labeling steps, since we can detect sparsely labeled classes (semi-supervised) and identify emerging classes hidden in the data (unsupervised). We demonstrate the efficacy of our approach with established time series classification datasets from different domains.

  @article{davidson2022semiunsupervised, abstract = {Time series are ubiquitous and therefore inherently hard to analyze and ultimately to label or cluster. With the rise of the Internet of Things (IoT) and its smart devices, data is collected in large amounts any given second. The collected data is rich in information, as one can detect accidents (e.g. cars) in real time, or assess injury/sickness over a given time span (e.g. health devices). Due to its chaotic nature and massive amounts of datapoints, timeseries are hard to label manually. Furthermore new classes within the data could emerge over time (contrary to e.g. handwritten digits), which would require relabeling the data. In this paper we present SuSL4TS, a deep generative Gaussian mixture model for semi-unsupervised learning, to classify time series data. With our approach we can alleviate manual labeling steps, since we can detect sparsely labeled classes (semi-supervised) and identify emerging classes hidden in the data (unsupervised). We demonstrate the efficacy of our approach with established time series classification datasets from different domains.}, author = {Davidson, Padraig and Steininger, Michael and Huhn, André and Krause, Anna and Hotho, Andreas}, journal = {Milets@KDD}, keywords = {timeseries}, publisher = {arXiv}, title = {Semi-unsupervised Learning for Time Series Classification}, year = 2022 }

  %0 Journal Article %1 davidson2022semiunsupervised %A Davidson, Padraig %A Steininger, Michael %A Huhn, André %A Krause, Anna %A Hotho, Andreas %D 2022 %I arXiv %J Milets@KDD %R 10.48550/ARXIV.2207.03119 %T Semi-unsupervised Learning for Time Series Classification %U https://arxiv.org/abs/2207.03119 %X Time series are ubiquitous and therefore inherently hard to analyze and ultimately to label or cluster. With the rise of the Internet of Things (IoT) and its smart devices, data is collected in large amounts any given second. The collected data is rich in information, as one can detect accidents (e.g. cars) in real time, or assess injury/sickness over a given time span (e.g. health devices). Due to its chaotic nature and massive amounts of datapoints, timeseries are hard to label manually. Furthermore new classes within the data could emerge over time (contrary to e.g. handwritten digits), which would require relabeling the data. In this paper we present SuSL4TS, a deep generative Gaussian mixture model for semi-unsupervised learning, to classify time series data. With our approach we can alleviate manual labeling steps, since we can detect sparsely labeled classes (semi-supervised) and identify emerging classes hidden in the data (unsupervised). We demonstrate the efficacy of our approach with established time series classification datasets from different domains.
• 
  Open ERP System Data For Occupational Fraud Detection Tritscher, Julian; Gwinner, Fabian; Schlör, Daniel; Krause, Anna; Hotho, Andreas in arxiv (2022).
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{tritscher2022erpData, author = {Tritscher, Julian and Gwinner, Fabian and Schlör, Daniel and Krause, Anna and Hotho, Andreas}, journal = {arxiv}, keywords = {from:tritsch}, title = {Open ERP System Data For Occupational Fraud Detection}, year = 2022 }

  %0 Journal Article %1 tritscher2022erpData %A Tritscher, Julian %A Gwinner, Fabian %A Schlör, Daniel %A Krause, Anna %A Hotho, Andreas %D 2022 %J arxiv %T Open ERP System Data For Occupational Fraud Detection %U https://arxiv.org/abs/2206.04460
• 
  Detecting Anomalies in Transaction Data Schlör, Daniel PhD thesis, Universität Würzburg. (2022).
  • [ BibTeX ]
  • [ EndNote ]
  @phdthesis{Schloer2022, author = {Schlör, Daniel}, keywords = {from:daschloer}, school = {Universität Würzburg}, title = {Detecting Anomalies in Transaction Data}, type = {Doctoral Thesis}, year = 2022 }

  %0 Thesis %1 Schloer2022 %A Schlör, Daniel %D 2022 %R 10.25972/OPUS-29856 %T Detecting Anomalies in Transaction Data

• 
  Comparison of Transformer-Based Sequential Product Recommendation Models for the Coveo Data Challenge Fischer, Elisabeth; Zoller, Daniel; Hotho, Andreas in SIGIR Workshop On eCommerce (2021).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{fischer2021comparison, author = {Fischer, Elisabeth and Zoller, Daniel and Hotho, Andreas}, journal = {SIGIR Workshop On eCommerce}, keywords = {transformer}, month = {July}, title = {Comparison of Transformer-Based Sequential Product Recommendation Models for the Coveo Data Challenge}, year = 2021 }

  %0 Journal Article %1 fischer2021comparison %A Fischer, Elisabeth %A Zoller, Daniel %A Hotho, Andreas %D 2021 %J SIGIR Workshop On eCommerce %T Comparison of Transformer-Based Sequential Product Recommendation Models for the Coveo Data Challenge
• 
  Anomaly Detection in Beehives: An Algorithm Comparison Davidson, Padraig; Steininger, Michael; Lautenschlager, Florian; Krause, Anna; Hotho, Andreas (2021).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @misc{davidson2021anomaly, author = {Davidson, Padraig and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas}, keywords = {from:pdavidson}, title = {Anomaly Detection in Beehives: An Algorithm Comparison}, year = 2021 }

  %0 Generic %1 davidson2021anomaly %A Davidson, Padraig %A Steininger, Michael %A Lautenschlager, Florian %A Krause, Anna %A Hotho, Andreas %D 2021 %T Anomaly Detection in Beehives: An Algorithm Comparison
• 
  Learning Mathematical Relations Using Deep Tree Models Wankerl, Sebastian; Dulny, Andrzej; Götz, Gerhard; Hotho, Andreas in 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) (2021). 1681–1687.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  To the present day, computer algebra systems used for calculating mathematical relations on a symbolic level are mainly rule-based systems. Only recently, deep learning has been applied to the task of symbolic mathematics. Researchers succeeded in developing neural networks which can do symbolic calculations of the equivalence of multiple pairing of equations. However, the generator used to create mathematical terms in previous research has several drawbacks and as with all deep learning tasks, the quality of the data used for training the models has a significant impact on the quality of the results. In this work, we propose a new generator for polynomials. We use it to train several recursive neural networks to recognize the equivalence, derivative, or variable substitution between pairs of polynomials for the first time. Our results indicate that these mathematical relations are identifiable with the help of deep learning.

  @inproceedings{9680206, abstract = {To the present day, computer algebra systems used for calculating mathematical relations on a symbolic level are mainly rule-based systems. Only recently, deep learning has been applied to the task of symbolic mathematics. Researchers succeeded in developing neural networks which can do symbolic calculations of the equivalence of multiple pairing of equations. However, the generator used to create mathematical terms in previous research has several drawbacks and as with all deep learning tasks, the quality of the data used for training the models has a significant impact on the quality of the results. In this work, we propose a new generator for polynomials. We use it to train several recursive neural networks to recognize the equivalence, derivative, or variable substitution between pairs of polynomials for the first time. Our results indicate that these mathematical relations are identifiable with the help of deep learning.}, author = {Wankerl, Sebastian and Dulny, Andrzej and Götz, Gerhard and Hotho, Andreas}, booktitle = {2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)}, keywords = {treemodels}, month = {dec}, pages = {1681-1687}, title = {Learning Mathematical Relations Using Deep Tree Models}, year = 2021 }

  %0 Conference Paper %1 9680206 %A Wankerl, Sebastian %A Dulny, Andrzej %A Götz, Gerhard %A Hotho, Andreas %B 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) %D 2021 %P 1681-1687 %R 10.1109/ICMLA52953.2021.00268 %T Learning Mathematical Relations Using Deep Tree Models %U https://ieeexplore.ieee.org/document/9680206 %X To the present day, computer algebra systems used for calculating mathematical relations on a symbolic level are mainly rule-based systems. Only recently, deep learning has been applied to the task of symbolic mathematics. Researchers succeeded in developing neural networks which can do symbolic calculations of the equivalence of multiple pairing of equations. However, the generator used to create mathematical terms in previous research has several drawbacks and as with all deep learning tasks, the quality of the data used for training the models has a significant impact on the quality of the results. In this work, we propose a new generator for polynomials. We use it to train several recursive neural networks to recognize the equivalence, derivative, or variable substitution between pairs of polynomials for the first time. Our results indicate that these mathematical relations are identifiable with the help of deep learning.
• 
  The {F}airy{N}et Corpus - Character Networks for {G}erman Fairy Tales Schmidt, David; Zehe, Albin; Lorenzen, Janne; Sergel, Lisa; D{\"u}ker, Sebastian; Krug, Markus; Puppe, Frank in Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (2021). 49–56.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  This paper presents a data set of German fairy tales, manually annotated with character networks which were obtained with high inter rater agreement. The release of this corpus provides an opportunity of training and comparing different algorithms for the extraction of character networks, which so far was barely possible due to heterogeneous interests of previous researchers. We demonstrate the usefulness of our data set by providing baseline experiments for the automatic extraction of character networks, applying a rule-based pipeline as well as a neural approach, and find the neural approach outperforming the rule-approach in most evaluation settings.

  @inproceedings{schmidt2021fairynet, abstract = {This paper presents a data set of German fairy tales, manually annotated with character networks which were obtained with high inter rater agreement. The release of this corpus provides an opportunity of training and comparing different algorithms for the extraction of character networks, which so far was barely possible due to heterogeneous interests of previous researchers. We demonstrate the usefulness of our data set by providing baseline experiments for the automatic extraction of character networks, applying a rule-based pipeline as well as a neural approach, and find the neural approach outperforming the rule-approach in most evaluation settings.}, address = {Punta Cana, Dominican Republic (online)}, author = {Schmidt, David and Zehe, Albin and Lorenzen, Janne and Sergel, Lisa and D{\"u}ker, Sebastian and Krug, Markus and Puppe, Frank}, booktitle = {Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature}, keywords = {from:albinzehe}, month = {nov}, pages = {49–56}, publisher = {Association for Computational Linguistics}, title = {The {F}airy{N}et Corpus - Character Networks for {G}erman Fairy Tales}, year = 2021 }

  %0 Conference Paper %1 schmidt2021fairynet %A Schmidt, David %A Zehe, Albin %A Lorenzen, Janne %A Sergel, Lisa %A D{\"u}ker, Sebastian %A Krug, Markus %A Puppe, Frank %B Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature %C Punta Cana, Dominican Republic (online) %D 2021 %I Association for Computational Linguistics %P 49--56 %R 10.18653/v1/2021.latechclfl-1.6 %T The {F}airy{N}et Corpus - Character Networks for {G}erman Fairy Tales %U https://aclanthology.org/2021.latechclfl-1.6 %X This paper presents a data set of German fairy tales, manually annotated with character networks which were obtained with high inter rater agreement. The release of this corpus provides an opportunity of training and comparing different algorithms for the extraction of character networks, which so far was barely possible due to heterogeneous interests of previous researchers. We demonstrate the usefulness of our data set by providing baseline experiments for the automatic extraction of character networks, applying a rule-based pipeline as well as a neural approach, and find the neural approach outperforming the rule-approach in most evaluation settings.
• 
  NeuralPDE: Modelling Dynamical Systems from Data Dulny, Andrzej; Hotho, Andreas; Krause, Anna (2021).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs). Modelling such dynamical systems using Neural Networks is an emerging research field. However, current methods are restricted in various ways: they require prior knowledge about the governing equations, and are limited to linear or first-order equations. In this work we propose NeuralPDE, a model which combines convolutional neural networks (CNNs) with differentiable ODE solvers to model dynamical systems. We show that the Method of Lines used in standard PDE solvers can be represented using convolutions which makes CNNs the natural choice to parametrize arbitrary PDE dynamics. Our model can be applied to any data without requiring any prior knowledge about the governing PDE. We evaluate NeuralPDE on datasets generated by solving a wide variety of PDEs, covering higher orders, non-linear equations and multiple spatial dimensions.

  @misc{dulny2021neuralpde, abstract = {Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs). Modelling such dynamical systems using Neural Networks is an emerging research field. However, current methods are restricted in various ways: they require prior knowledge about the governing equations, and are limited to linear or first-order equations. In this work we propose NeuralPDE, a model which combines convolutional neural networks (CNNs) with differentiable ODE solvers to model dynamical systems. We show that the Method of Lines used in standard PDE solvers can be represented using convolutions which makes CNNs the natural choice to parametrize arbitrary PDE dynamics. Our model can be applied to any data without requiring any prior knowledge about the governing PDE. We evaluate NeuralPDE on datasets generated by solving a wide variety of PDEs, covering higher orders, non-linear equations and multiple spatial dimensions.}, author = {Dulny, Andrzej and Hotho, Andreas and Krause, Anna}, keywords = {pde}, note = {cite arxiv:2111.07671}, title = {NeuralPDE: Modelling Dynamical Systems from Data}, year = 2021 }

  %0 Generic %1 dulny2021neuralpde %A Dulny, Andrzej %A Hotho, Andreas %A Krause, Anna %D 2021 %T NeuralPDE: Modelling Dynamical Systems from Data %U http://arxiv.org/abs/2111.07671 %X Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs). Modelling such dynamical systems using Neural Networks is an emerging research field. However, current methods are restricted in various ways: they require prior knowledge about the governing equations, and are limited to linear or first-order equations. In this work we propose NeuralPDE, a model which combines convolutional neural networks (CNNs) with differentiable ODE solvers to model dynamical systems. We show that the Method of Lines used in standard PDE solvers can be represented using convolutions which makes CNNs the natural choice to parametrize arbitrary PDE dynamics. Our model can be applied to any data without requiring any prior knowledge about the governing PDE. We evaluate NeuralPDE on datasets generated by solving a wide variety of PDEs, covering higher orders, non-linear equations and multiple spatial dimensions.
• 
  The Semantic Web - {ISWC} 2021 - 20th International Semantic Web Conference, {ISWC} 2021, Virtual Event, October 24-28, 2021, Proceedings Hotho, Andreas; Blomqvist, Eva; Dietze, Stefan; Fokoue, Achille; Ding, Ying; Barnaghi, Payam M.; Haller, Armin; Dragoni, Mauro; Alani, Harith in Lecture Notes in Computer Science (2021). (Vol. 12922) Springer.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @proceedings{DBLP:conf/semweb/2021, editor = {Hotho, Andreas and Blomqvist, Eva and Dietze, Stefan and Fokoue, Achille and Ding, Ying and Barnaghi, Payam M. and Haller, Armin and Dragoni, Mauro and Alani, Harith}, keywords = {from:hotho}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {The Semantic Web - {ISWC} 2021 - 20th International Semantic Web Conference, {ISWC} 2021, Virtual Event, October 24-28, 2021, Proceedings}, volume = 12922, year = 2021 }

  %0 Conference Proceedings %1 DBLP:conf/semweb/2021 %B Lecture Notes in Computer Science %D 2021 %E Hotho, Andreas %E Blomqvist, Eva %E Dietze, Stefan %E Fokoue, Achille %E Ding, Ying %E Barnaghi, Payam M. %E Haller, Armin %E Dragoni, Mauro %E Alani, Harith %I Springer %R 10.1007/978-3-030-88361-4 %T The Semantic Web - {ISWC} 2021 - 20th International Semantic Web Conference, {ISWC} 2021, Virtual Event, October 24-28, 2021, Proceedings %U https://doi.org/10.1007/978-3-030-88361-4 %V 12922 %@ 978-3-030-88360-7
• 
  Sequential Item Recommendation in the MOBA Game Dota 2 Dallmann, Alexander; Kohlmann, Johannes; Zoller, Daniel; Hotho, Andreas in 2021 International Conference on Data Mining Workshops (ICDMW) (2021). 10–17.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  Multiplayer Online Battle Arena (MOBA) games such as Dota 2 attract hundreds of thousands of players every year. Despite the large player base, it is still important to attract new players to prevent the community of a game from becoming inactive. Entering MOBA games is, however, often demanding, requiring the player to learn numerous skills at once. An important factor of success is buying the correct items which forms a complex task depending on various in-game factors such as already purchased items, the team composition, or available resources. A recommendation system can support players by reducing the mental effort required to choose a suitable item, helping, e.g., newer players or players returning to the game after a longer break, to focus on other aspects of the game. Since Sequential Item Recommendation (SIR) has proven to be effective in various domains (e.g. e-commerce, movie recommendation or playlist continuation), we explore the applicability of well-known SIR models in the context of purchase recommendations in Dota 2. To facilitate this research, we collect, analyze and publish Dota-350k, a new large dataset based on recent Dota 2 matches. We find that SIR models can be employed effectively for item recommendation in Dota 2. Our results show that models that consider the order of purchases are the most effective. In contrast to other domains, we find RNN-based models to outperform the more recent Transformer-based architectures on Dota-350k.

  @inproceedings{9679858, abstract = {Multiplayer Online Battle Arena (MOBA) games such as Dota 2 attract hundreds of thousands of players every year. Despite the large player base, it is still important to attract new players to prevent the community of a game from becoming inactive. Entering MOBA games is, however, often demanding, requiring the player to learn numerous skills at once. An important factor of success is buying the correct items which forms a complex task depending on various in-game factors such as already purchased items, the team composition, or available resources. A recommendation system can support players by reducing the mental effort required to choose a suitable item, helping, e.g., newer players or players returning to the game after a longer break, to focus on other aspects of the game. Since Sequential Item Recommendation (SIR) has proven to be effective in various domains (e.g. e-commerce, movie recommendation or playlist continuation), we explore the applicability of well-known SIR models in the context of purchase recommendations in Dota 2. To facilitate this research, we collect, analyze and publish Dota-350k, a new large dataset based on recent Dota 2 matches. We find that SIR models can be employed effectively for item recommendation in Dota 2. Our results show that models that consider the order of purchases are the most effective. In contrast to other domains, we find RNN-based models to outperform the more recent Transformer-based architectures on Dota-350k.}, author = {Dallmann, Alexander and Kohlmann, Johannes and Zoller, Daniel and Hotho, Andreas}, booktitle = {2021 International Conference on Data Mining Workshops (ICDMW)}, keywords = {from:hotho}, month = {dec}, pages = {10-17}, title = {Sequential Item Recommendation in the MOBA Game Dota 2}, year = 2021 }

  %0 Conference Paper %1 9679858 %A Dallmann, Alexander %A Kohlmann, Johannes %A Zoller, Daniel %A Hotho, Andreas %B 2021 International Conference on Data Mining Workshops (ICDMW) %D 2021 %P 10-17 %R 10.1109/ICDMW53433.2021.00009 %T Sequential Item Recommendation in the MOBA Game Dota 2 %X Multiplayer Online Battle Arena (MOBA) games such as Dota 2 attract hundreds of thousands of players every year. Despite the large player base, it is still important to attract new players to prevent the community of a game from becoming inactive. Entering MOBA games is, however, often demanding, requiring the player to learn numerous skills at once. An important factor of success is buying the correct items which forms a complex task depending on various in-game factors such as already purchased items, the team composition, or available resources. A recommendation system can support players by reducing the mental effort required to choose a suitable item, helping, e.g., newer players or players returning to the game after a longer break, to focus on other aspects of the game. Since Sequential Item Recommendation (SIR) has proven to be effective in various domains (e.g. e-commerce, movie recommendation or playlist continuation), we explore the applicability of well-known SIR models in the context of purchase recommendations in Dota 2. To facilitate this research, we collect, analyze and publish Dota-350k, a new large dataset based on recent Dota 2 matches. We find that SIR models can be employed effectively for item recommendation in Dota 2. Our results show that models that consider the order of purchases are the most effective. In contrast to other domains, we find RNN-based models to outperform the more recent Transformer-based architectures on Dota-350k.
• 
  Malware detection on windows audit logs using LSTMs Ring, Markus; Schlör, Daniel; Wunderlich, Sarah; Landes, Dieter; Hotho, Andreas in Computers & Security (2021). 109 102389.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  Malware is a constant threat and is continuously evolving. Security systems try to keep up with the constant change. One challenge that arises is the large amount of logs generated on an operating system and the need to clarify which information contributes to the detection of possible malware. This work aims at the detection of malware using neural networks based on Windows audit log events. Neural networks can only process continuous data, but Windows audit logs are sequential and textual data. To address these challenges, we extract features out of the audit log events and use LSTMs to capture sequential effects. We create different subsets of features and analyze the effects of additional information. Features describe for example the action-type of windows audit log events, process names or target files that are accessed. Textual features are represented either as one-hot encoding or embedding representation, for which we compare three different approaches for representation learning. Effects of different feature subsets and representations are evaluated on a publicly available data set. Results indicate that using additional information improves the performance of the LSTM-model. While different representations lead to similar classification results, analysis of the latent space shows differences more precisely where FastText seems to be the most promising representation.

  @article{RING2021102389, abstract = {Malware is a constant threat and is continuously evolving. Security systems try to keep up with the constant change. One challenge that arises is the large amount of logs generated on an operating system and the need to clarify which information contributes to the detection of possible malware. This work aims at the detection of malware using neural networks based on Windows audit log events. Neural networks can only process continuous data, but Windows audit logs are sequential and textual data. To address these challenges, we extract features out of the audit log events and use LSTMs to capture sequential effects. We create different subsets of features and analyze the effects of additional information. Features describe for example the action-type of windows audit log events, process names or target files that are accessed. Textual features are represented either as one-hot encoding or embedding representation, for which we compare three different approaches for representation learning. Effects of different feature subsets and representations are evaluated on a publicly available data set. Results indicate that using additional information improves the performance of the LSTM-model. While different representations lead to similar classification results, analysis of the latent space shows differences more precisely where FastText seems to be the most promising representation.}, author = {Ring, Markus and Schlör, Daniel and Wunderlich, Sarah and Landes, Dieter and Hotho, Andreas}, journal = {Computers & Security}, keywords = {from:hotho}, pages = 102389, title = {Malware detection on windows audit logs using LSTMs}, volume = 109, year = 2021 }

  %0 Journal Article %1 RING2021102389 %A Ring, Markus %A Schlör, Daniel %A Wunderlich, Sarah %A Landes, Dieter %A Hotho, Andreas %D 2021 %J Computers & Security %P 102389 %R https://doi.org/10.1016/j.cose.2021.102389 %T Malware detection on windows audit logs using LSTMs %U https://www.sciencedirect.com/science/article/pii/S0167404821002133 %V 109 %X Malware is a constant threat and is continuously evolving. Security systems try to keep up with the constant change. One challenge that arises is the large amount of logs generated on an operating system and the need to clarify which information contributes to the detection of possible malware. This work aims at the detection of malware using neural networks based on Windows audit log events. Neural networks can only process continuous data, but Windows audit logs are sequential and textual data. To address these challenges, we extract features out of the audit log events and use LSTMs to capture sequential effects. We create different subsets of features and analyze the effects of additional information. Features describe for example the action-type of windows audit log events, process names or target files that are accessed. Textual features are represented either as one-hot encoding or embedding representation, for which we compare three different approaches for representation learning. Effects of different feature subsets and representations are evaluated on a publicly available data set. Results indicate that using additional information improves the performance of the LSTM-model. While different representations lead to similar classification results, analysis of the latent space shows differences more precisely where FastText seems to be the most promising representation.
• 
  DETECTING PRESENCE OF SPEECH IN ACOUSTIC DATA OBTAINED FROM BEEHIVES Janetzky, Pascal; Davidson, Padraig; Steininger, Michael; Krause, Anna; Hotho, Andreas in DCASE Workshop (2021).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{janetzkydetecting, author = {Janetzky, Pascal and Davidson, Padraig and Steininger, Michael and Krause, Anna and Hotho, Andreas}, journal = {DCASE Workshop}, keywords = {from:msteininger}, title = {DETECTING PRESENCE OF SPEECH IN ACOUSTIC DATA OBTAINED FROM BEEHIVES}, year = 2021 }

  %0 Journal Article %1 janetzkydetecting %A Janetzky, Pascal %A Davidson, Padraig %A Steininger, Michael %A Krause, Anna %A Hotho, Andreas %D 2021 %J DCASE Workshop %T DETECTING PRESENCE OF SPEECH IN ACOUSTIC DATA OBTAINED FROM BEEHIVES
• 
  Shared Task on Scene Segmentation @ KONVENS 2021 Zehe, Albin; Konle, Leonard; Guhr, Svenja; Dümpelmann, Lea; Gius, Evelyn; Hotho, Andreas; Jannidis, Fotis; Kaufmann, Lucas; Krug, Markus; Puppe, Frank; Reiter, Nils; Schreiber, Annekea in Shared Task on Scene Segmentation @ KONVENS 2021 (2021). 1–21.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{zehe2021shared, author = {Zehe, Albin and Konle, Leonard and Guhr, Svenja and Dümpelmann, Lea and Gius, Evelyn and Hotho, Andreas and Jannidis, Fotis and Kaufmann, Lucas and Krug, Markus and Puppe, Frank and Reiter, Nils and Schreiber, Annekea}, booktitle = {Shared Task on Scene Segmentation @ KONVENS 2021}, keywords = {from:albinzehe}, pages = {1-21}, title = {Shared Task on Scene Segmentation @ KONVENS 2021}, year = 2021 }

  %0 Conference Paper %1 zehe2021shared %A Zehe, Albin %A Konle, Leonard %A Guhr, Svenja %A Dümpelmann, Lea %A Gius, Evelyn %A Hotho, Andreas %A Jannidis, Fotis %A Kaufmann, Lucas %A Krug, Markus %A Puppe, Frank %A Reiter, Nils %A Schreiber, Annekea %B Shared Task on Scene Segmentation @ KONVENS 2021 %D 2021 %P 1-21 %T Shared Task on Scene Segmentation @ KONVENS 2021 %U http://ceur-ws.org/Vol-3001/paper1.pdf
• 
  A financial game with opportunities for fraud Tritscher, Julian; Krause, Anna; Schlör, Daniel; Gwinner, Fabian; Von Mammen, Sebastian; Hotho, Andreas in 2021 IEEE Conference on Games (CoG) (2021). 1–5.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @inproceedings{Tritscher:2021aa, author = {Tritscher, Julian and Krause, Anna and Schlör, Daniel and Gwinner, Fabian and Von Mammen, Sebastian and Hotho, Andreas}, booktitle = {2021 IEEE Conference on Games (CoG)}, keywords = {from:daschloer}, pages = {1-5}, title = {A financial game with opportunities for fraud}, year = 2021 }

  %0 Conference Paper %1 Tritscher:2021aa %A Tritscher, Julian %A Krause, Anna %A Schlör, Daniel %A Gwinner, Fabian %A Von Mammen, Sebastian %A Hotho, Andreas %B 2021 IEEE Conference on Games (CoG) %D 2021 %P 1-5 %R 10.1109/CoG52621.2021.9619070 %T A financial game with opportunities for fraud %U https://downloads.hci.informatik.uni-wuerzburg.de/Tritscher2021aa.pdf
• 
  CoBERT: Scientific Collaboration Prediction via Sequential Recommendation Koopmann, Tobias; Kobs, Konstantin; Herud, Konstantin; Hotho, Andreas in 2021 International Conference on Data Mining Workshops (ICDMW) (2021). 45–54.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Collaborations are an Important factor for scientific success, as the joint work leads to results individual scientists cannot easily reach. Recommending collaborations automatically can alleviate the time consuming and tedious search for potential collaborators. Usually, such recommendation systems rely on graph structures modeling co-authorship of papers and content-based relations such as similar paper keywords. Models are then trained to estimate the probability of links between certain authors in these graphs.In this paper, we argue that the order of papers is crucial for reliably predicting future collaborations, which is not considered by graph-based recommendation systems. We thus propose to reformulate the task of collaboration recommendation as a sequential recommendation task. Here, we aim to predict the next co-author in a chronologically sorted sequence of an author’s collaborators. We introduce CoBERT, a BERT4Rec inspired model, that predicts the sequence’s next co-author and thus a potential collaborator. Since the order of co-authors of a single paper is not that important compared to the overall paper order, we leverage positional embeddings encoding paper positions instead of co-author positions in the sequence. Additionally, we inject content features about every paper and their co-authors. We evaluate CoBERT on two datasets consisting of papers from the field of Artificial Intelligence and the journal PlosOne. We show that CoBERT can outperform graph-based methods and BERT4Rec when predicting the co-authors of the next paper. We make our code and data available.

  @inproceedings{koopmann2021cobert, abstract = {Collaborations are an Important factor for scientific success, as the joint work leads to results individual scientists cannot easily reach. Recommending collaborations automatically can alleviate the time consuming and tedious search for potential collaborators. Usually, such recommendation systems rely on graph structures modeling co-authorship of papers and content-based relations such as similar paper keywords. Models are then trained to estimate the probability of links between certain authors in these graphs.In this paper, we argue that the order of papers is crucial for reliably predicting future collaborations, which is not considered by graph-based recommendation systems. We thus propose to reformulate the task of collaboration recommendation as a sequential recommendation task. Here, we aim to predict the next co-author in a chronologically sorted sequence of an author’s collaborators. We introduce CoBERT, a BERT4Rec inspired model, that predicts the sequence’s next co-author and thus a potential collaborator. Since the order of co-authors of a single paper is not that important compared to the overall paper order, we leverage positional embeddings encoding paper positions instead of co-author positions in the sequence. Additionally, we inject content features about every paper and their co-authors. We evaluate CoBERT on two datasets consisting of papers from the field of Artificial Intelligence and the journal PlosOne. We show that CoBERT can outperform graph-based methods and BERT4Rec when predicting the co-authors of the next paper. We make our code and data available.}, author = {Koopmann, Tobias and Kobs, Konstantin and Herud, Konstantin and Hotho, Andreas}, booktitle = {2021 International Conference on Data Mining Workshops (ICDMW)}, keywords = {from:tobias.koopmann}, month = {dec}, pages = {45-54}, title = {CoBERT: Scientific Collaboration Prediction via Sequential Recommendation}, year = 2021 }

  %0 Conference Paper %1 koopmann2021cobert %A Koopmann, Tobias %A Kobs, Konstantin %A Herud, Konstantin %A Hotho, Andreas %B 2021 International Conference on Data Mining Workshops (ICDMW) %D 2021 %P 45-54 %R 10.1109/ICDMW53433.2021.00013 %T CoBERT: Scientific Collaboration Prediction via Sequential Recommendation %X Collaborations are an Important factor for scientific success, as the joint work leads to results individual scientists cannot easily reach. Recommending collaborations automatically can alleviate the time consuming and tedious search for potential collaborators. Usually, such recommendation systems rely on graph structures modeling co-authorship of papers and content-based relations such as similar paper keywords. Models are then trained to estimate the probability of links between certain authors in these graphs.In this paper, we argue that the order of papers is crucial for reliably predicting future collaborations, which is not considered by graph-based recommendation systems. We thus propose to reformulate the task of collaboration recommendation as a sequential recommendation task. Here, we aim to predict the next co-author in a chronologically sorted sequence of an author’s collaborators. We introduce CoBERT, a BERT4Rec inspired model, that predicts the sequence’s next co-author and thus a potential collaborator. Since the order of co-authors of a single paper is not that important compared to the overall paper order, we leverage positional embeddings encoding paper positions instead of co-author positions in the sequence. Additionally, we inject content features about every paper and their co-authors. We evaluate CoBERT on two datasets consisting of papers from the field of Artificial Intelligence and the journal PlosOne. We show that CoBERT can outperform graph-based methods and BERT4Rec when predicting the co-authors of the next paper. We make our code and data available.
• 
  Evaluating the multi-task learning approach for land use regression modelling of air pollution Dulny, Andrzej; Steininger, Michael; Lautenschlager, Florian; Krause, Anna; Hotho, Andreas in Journal of Physics: Conference Series (2021). 1834(1) 012004.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.

  @article{dulny2021evaluating, abstract = {Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.}, author = {Dulny, Andrzej and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas}, journal = {Journal of Physics: Conference Series}, keywords = {from:msteininger}, month = {mar}, number = 1, organization = {IOP Publishing}, pages = {012004}, publisher = {{IOP} Publishing}, title = {Evaluating the multi-task learning approach for land use regression modelling of air pollution}, volume = 1834, year = 2021 }

  %0 Journal Article %1 dulny2021evaluating %A Dulny, Andrzej %A Steininger, Michael %A Lautenschlager, Florian %A Krause, Anna %A Hotho, Andreas %D 2021 %I {IOP} Publishing %J Journal of Physics: Conference Series %N 1 %P 012004 %R 10.1088/1742-6596/1834/1/012004 %T Evaluating the multi-task learning approach for land use regression modelling of air pollution %U https://doi.org/10.1088/1742-6596/1834/1/012004 %V 1834 %X Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.
• 
  Do Different Deep Metric Learning Losses Lead to Similar Learned Features? Kobs, Konstantin; Steininger, Michael; Dulny, Andrzej; Hotho, Andreas in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021). 10644–10654.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{noauthororeditor, author = {Kobs, Konstantin and Steininger, Michael and Dulny, Andrzej and Hotho, Andreas}, journal = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, keywords = {myown}, month = {October}, pages = {10644-10654}, title = {Do Different Deep Metric Learning Losses Lead to Similar Learned Features?}, year = 2021 }

  %0 Journal Article %1 noauthororeditor %A Kobs, Konstantin %A Steininger, Michael %A Dulny, Andrzej %A Hotho, Andreas %D 2021 %J Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) %P 10644-10654 %T Do Different Deep Metric Learning Losses Lead to Similar Learned Features?
• 
  Automating the optical identification of abrasive wear on electrical contact pins Buckermann, Florian; Klement, Nils; Beyer, Oliver; Hütten, Andreas; Hammer, Barbara in at - Automatisierungstechnik (2021). 69(10) 903–914.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  The automation of quality control in manufacturing has made great strides in recent years, in particular following new developments in machine learning, specifically deep learning, which allow to solve challenging tasks such as visual inspection or quality prediction. Yet, optimum quality control pipelines are often not obvious in specific settings, since they do not necessarily align with (supervised) machine learning tasks. In this contribution, we introduce a new automation pipeline for the quantification of wear on electrical contact pins. More specifically, we propose and test a novel pipeline which combines a deep network for image segmentation with geometric priors of the problem. This task is important for a judgement of the quality of the material and it can serve as a starting point to optimize the choices of materials based on its automated evaluation.

  @article{BuckermannKlementBeyerHüttenHammer+2021+903+914, abstract = {The automation of quality control in manufacturing has made great strides in recent years, in particular following new developments in machine learning, specifically deep learning, which allow to solve challenging tasks such as visual inspection or quality prediction. Yet, optimum quality control pipelines are often not obvious in specific settings, since they do not necessarily align with (supervised) machine learning tasks. In this contribution, we introduce a new automation pipeline for the quantification of wear on electrical contact pins. More specifically, we propose and test a novel pipeline which combines a deep network for image segmentation with geometric priors of the problem. This task is important for a judgement of the quality of the material and it can serve as a starting point to optimize the choices of materials based on its automated evaluation.}, author = {Buckermann, Florian and Klement, Nils and Beyer, Oliver and Hütten, Andreas and Hammer, Barbara}, journal = {at - Automatisierungstechnik}, keywords = {from:fbuckermann}, number = 10, pages = {903–914}, title = {Automating the optical identification of abrasive wear on electrical contact pins}, volume = 69, year = 2021 }

  %0 Journal Article %1 BuckermannKlementBeyerHüttenHammer+2021+903+914 %A Buckermann, Florian %A Klement, Nils %A Beyer, Oliver %A Hütten, Andreas %A Hammer, Barbara %D 2021 %J at - Automatisierungstechnik %N 10 %P 903--914 %R doi:10.1515/auto-2021-0021 %T Automating the optical identification of abrasive wear on electrical contact pins %U https://doi.org/10.1515/auto-2021-0021 %V 69 %X The automation of quality control in manufacturing has made great strides in recent years, in particular following new developments in machine learning, specifically deep learning, which allow to solve challenging tasks such as visual inspection or quality prediction. Yet, optimum quality control pipelines are often not obvious in specific settings, since they do not necessarily align with (supervised) machine learning tasks. In this contribution, we introduce a new automation pipeline for the quantification of wear on electrical contact pins. More specifically, we propose and test a novel pipeline which combines a deep network for image segmentation with geometric priors of the problem. This task is important for a judgement of the quality of the material and it can serve as a starting point to optimize the choices of materials based on its automated evaluation.
• 
  Proximity dimensions and the emergence of collaboration: a HypTrails study on German AI research Koopmann, Tobias; Stubbemann, Maximilian; Kapa, Matthias; Paris, Michael; Buenstorf, Guido; Hanika, Tom; Hotho, Andreas; Jäschke, Robert; Stumme, Gerd in Scientometrics (2021).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Creation and exchange of knowledge depends on collaboration. Recent work has suggested that the emergence of collaboration frequently relies on geographic proximity. However, being co-located tends to be associated with other dimensions of proximity, such as social ties or a shared organizational environment. To account for such factors, multiple dimensions of proximity have been proposed, including cognitive, institutional, organizational, social and geographical proximity. Since they strongly interrelate, disentangling these dimensions and their respective impact on collaboration is challenging. To address this issue, we propose various methods for measuring different dimensions of proximity. We then present an approach to compare and rank them with respect to the extent to which they indicate co-publications and co-inventions. We adapt the HypTrails approach, which was originally developed to explain human navigation, to co-author and co-inventor graphs. We evaluate this approach on a subset of the German research community, specifically academic authors and inventors active in research on artificial intelligence (AI). We find that social proximity and cognitive proximity are more important for the emergence of collaboration than geographic proximity.

  @article{koopmann2021proximity, abstract = {Creation and exchange of knowledge depends on collaboration. Recent work has suggested that the emergence of collaboration frequently relies on geographic proximity. However, being co-located tends to be associated with other dimensions of proximity, such as social ties or a shared organizational environment. To account for such factors, multiple dimensions of proximity have been proposed, including cognitive, institutional, organizational, social and geographical proximity. Since they strongly interrelate, disentangling these dimensions and their respective impact on collaboration is challenging. To address this issue, we propose various methods for measuring different dimensions of proximity. We then present an approach to compare and rank them with respect to the extent to which they indicate co-publications and co-inventions. We adapt the HypTrails approach, which was originally developed to explain human navigation, to co-author and co-inventor graphs. We evaluate this approach on a subset of the German research community, specifically academic authors and inventors active in research on artificial intelligence (AI). We find that social proximity and cognitive proximity are more important for the emergence of collaboration than geographic proximity.}, author = {Koopmann, Tobias and Stubbemann, Maximilian and Kapa, Matthias and Paris, Michael and Buenstorf, Guido and Hanika, Tom and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, journal = {Scientometrics}, keywords = {from:tobias.koopmann}, title = {Proximity dimensions and the emergence of collaboration: a HypTrails study on German AI research}, year = 2021 }

  %0 Journal Article %1 koopmann2021proximity %A Koopmann, Tobias %A Stubbemann, Maximilian %A Kapa, Matthias %A Paris, Michael %A Buenstorf, Guido %A Hanika, Tom %A Hotho, Andreas %A Jäschke, Robert %A Stumme, Gerd %D 2021 %J Scientometrics %R 10.1007/s11192-021-03922-1 %T Proximity dimensions and the emergence of collaboration: a HypTrails study on German AI research %U https://doi.org/10.1007/s11192-021-03922-1 %X Creation and exchange of knowledge depends on collaboration. Recent work has suggested that the emergence of collaboration frequently relies on geographic proximity. However, being co-located tends to be associated with other dimensions of proximity, such as social ties or a shared organizational environment. To account for such factors, multiple dimensions of proximity have been proposed, including cognitive, institutional, organizational, social and geographical proximity. Since they strongly interrelate, disentangling these dimensions and their respective impact on collaboration is challenging. To address this issue, we propose various methods for measuring different dimensions of proximity. We then present an approach to compare and rank them with respect to the extent to which they indicate co-publications and co-inventions. We adapt the HypTrails approach, which was originally developed to explain human navigation, to co-author and co-inventor graphs. We evaluate this approach on a subset of the German research community, specifically academic authors and inventors active in research on artificial intelligence (AI). We find that social proximity and cognitive proximity are more important for the emergence of collaboration than geographic proximity.
• 
  Assessing Media Bias in Cross-Linguistic and Cross-National Populations Sales, Allan; Zehe, Albin; Marinho, Leandro Balby; Veloso, Adriano; Hotho, Andreas; Omeliyanenko, Janna in Proceedings of the International AAAI Conference on Web and Social Media (2021). 15(1) 561–572.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{sales2021assessing, author = {Sales, Allan and Zehe, Albin and Marinho, Leandro Balby and Veloso, Adriano and Hotho, Andreas and Omeliyanenko, Janna}, journal = {Proceedings of the International AAAI Conference on Web and Social Media}, keywords = {from:albinzehe}, month = {may}, number = 1, pages = {561-572}, title = {Assessing Media Bias in Cross-Linguistic and Cross-National Populations}, volume = 15, year = 2021 }

  %0 Journal Article %1 sales2021assessing %A Sales, Allan %A Zehe, Albin %A Marinho, Leandro Balby %A Veloso, Adriano %A Hotho, Andreas %A Omeliyanenko, Janna %D 2021 %J Proceedings of the International AAAI Conference on Web and Social Media %N 1 %P 561-572 %T Assessing Media Bias in Cross-Linguistic and Cross-National Populations %U https://ojs.aaai.org/index.php/ICWSM/article/view/18084 %V 15
• 
  Self-Supervised Multi-Task Pretraining Improves Image Aesthetic Assessment Pfister, Jan; Kobs, Konstantin; Hotho, Andreas in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2021). 816–825.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{Pfister_2021_CVPR, author = {Pfister, Jan and Kobs, Konstantin and Hotho, Andreas}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, keywords = {myown}, month = {June}, pages = {816-825}, title = {Self-Supervised Multi-Task Pretraining Improves Image Aesthetic Assessment}, year = 2021 }

  %0 Conference Paper %1 Pfister_2021_CVPR %A Pfister, Jan %A Kobs, Konstantin %A Hotho, Andreas %B Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops %D 2021 %P 816-825 %T Self-Supervised Multi-Task Pretraining Improves Image Aesthetic Assessment
• 
  Semi-Supervised Learning for Grain Size Distribution Interpolation Kobs, Konstantin; Schäfer, Christian; Steininger, Michael; Krause, Anna; Baumhauer, Roland; Paeth, Heiko; Hotho, Andreas in Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10--15, 2021, Proceedings, Part VI (2021). 34–44.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{kobs2021semi, author = {Kobs, Konstantin and Schäfer, Christian and Steininger, Michael and Krause, Anna and Baumhauer, Roland and Paeth, Heiko and Hotho, Andreas}, booktitle = {Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10–15, 2021, Proceedings, Part VI}, keywords = {from:konstantinkobs}, organization = {Springer International Publishing}, pages = {34–44}, title = {Semi-Supervised Learning for Grain Size Distribution Interpolation}, year = 2021 }

  %0 Conference Paper %1 kobs2021semi %A Kobs, Konstantin %A Schäfer, Christian %A Steininger, Michael %A Krause, Anna %A Baumhauer, Roland %A Paeth, Heiko %A Hotho, Andreas %B Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10--15, 2021, Proceedings, Part VI %D 2021 %P 34--44 %T Semi-Supervised Learning for Grain Size Distribution Interpolation
• 
  Density-based weighting for imbalanced regression Steininger, Michael; Kobs, Konstantin; Davidson, Padraig; Krause, Anna; Hotho, Andreas in Machine Learning, (A. Appice; S. Escalera; J. A. Gamez; H. Trautmann, eds.) (2021).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  In many real world settings,imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point’s influence on the loss according to DenseWeight, giving rare data points more influence on modeltraining compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.

  @article{steininger2021densitybased, abstract = {In many real world settings,imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point’s influence on the loss according to DenseWeight, giving rare data points more influence on modeltraining compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.}, author = {Steininger, Michael and Kobs, Konstantin and Davidson, Padraig and Krause, Anna and Hotho, Andreas}, editor = {Appice, Annalisa and Escalera, Sergio and Gamez, Jose A. and Trautmann, Heike}, journal = {Machine Learning}, keywords = {regression}, title = {Density-based weighting for imbalanced regression}, year = 2021 }

  %0 Journal Article %1 steininger2021densitybased %A Steininger, Michael %A Kobs, Konstantin %A Davidson, Padraig %A Krause, Anna %A Hotho, Andreas %D 2021 %E Appice, Annalisa %E Escalera, Sergio %E Gamez, Jose A. %E Trautmann, Heike %J Machine Learning %R 10.1007/s10994-021-06023-5 %T Density-based weighting for imbalanced regression %U https://doi.org/10.1007/s10994-021-06023-5 %X In many real world settings,imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point’s influence on the loss according to DenseWeight, giving rare data points more influence on modeltraining compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.
• 
  Detecting Scenes in Fiction: A new Segmentation Task Zehe, Albin; Konle, Leonard; Dümpelmann, Lea; Gius, Evelyn; Hotho, Andreas; Jannidis, Fotis; Kaufmann, Lucas; Krug, Markus; Puppe, Frank; Reiter, Nils; Schreiber, Annekea; Wiedmer, Nathalie in Proceedings of the 16th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers (2021).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{zehe2021detecting, author = {Zehe, Albin and Konle, Leonard and Dümpelmann, Lea and Gius, Evelyn and Hotho, Andreas and Jannidis, Fotis and Kaufmann, Lucas and Krug, Markus and Puppe, Frank and Reiter, Nils and Schreiber, Annekea and Wiedmer, Nathalie}, booktitle = {Proceedings of the 16th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers}, keywords = {from:albinzehe}, publisher = {ACL}, title = {Detecting Scenes in Fiction: A new Segmentation Task}, year = 2021 }

  %0 Conference Paper %1 zehe2021detecting %A Zehe, Albin %A Konle, Leonard %A Dümpelmann, Lea %A Gius, Evelyn %A Hotho, Andreas %A Jannidis, Fotis %A Kaufmann, Lucas %A Krug, Markus %A Puppe, Frank %A Reiter, Nils %A Schreiber, Annekea %A Wiedmer, Nathalie %B Proceedings of the 16th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers %D 2021 %I ACL %T Detecting Scenes in Fiction: A new Segmentation Task
• 
  A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models Dallmann, Alexander; Zoller, Daniel; Hotho, Andreas in Fifteenth {ACM} Conference on Recommender Systems (2021).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{dallmann2021study, author = {Dallmann, Alexander and Zoller, Daniel and Hotho, Andreas}, booktitle = {Fifteenth {ACM} Conference on Recommender Systems}, keywords = {from:dallmann}, month = {sep}, publisher = {{ACM}}, title = {A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models}, year = 2021 }

  %0 Conference Paper %1 dallmann2021study %A Dallmann, Alexander %A Zoller, Daniel %A Hotho, Andreas %B Fifteenth {ACM} Conference on Recommender Systems %D 2021 %I {ACM} %R 10.1145/3460231.3475943 %T A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models
• 
  A financial game with opportunities for fraud Tritscher, Julian; Krause, Anna; Schl{\"o}r, Daniel; Gwinner, Fabian; von Mammen, Sebastian; Hotho, Andreas in IEE COG 2021 (2021). 2021
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Even though companies store large amounts of business data in enterprise resource planning (ERP) systems, obtaining data for financial fraud detection is prohibitively difficult due to privacy concerns and companies protecting trade secrets. One possible solution is game-based generation of synthetic ERP data, which poses the challenge of designing an environment that generates realistic ERP data and allows players to commit many different types of fraud. In this work, we design a multiplayer game that allows players to cooperatively run a fictional company, while simultaneously challenging them to maximize their personal gain. We introduce an approach for letting players explore fraud scenarios through emergent gameplay and present a prototype that may be primed with information from real world ERP systems to generate realistic data.

  @article{tritscherfinancial, abstract = {Even though companies store large amounts of business data in enterprise resource planning (ERP) systems, obtaining data for financial fraud detection is prohibitively difficult due to privacy concerns and companies protecting trade secrets. One possible solution is game-based generation of synthetic ERP data, which poses the challenge of designing an environment that generates realistic ERP data and allows players to commit many different types of fraud. In this work, we design a multiplayer game that allows players to cooperatively run a fictional company, while simultaneously challenging them to maximize their personal gain. We introduce an approach for letting players explore fraud scenarios through emergent gameplay and present a prototype that may be primed with information from real world ERP systems to generate realistic data.}, author = {Tritscher, Julian and Krause, Anna and Schl{\"o}r, Daniel and Gwinner, Fabian and von Mammen, Sebastian and Hotho, Andreas}, journal = {IEE COG 2021}, keywords = {from:tritsch}, title = {A financial game with opportunities for fraud}, volume = 2021, year = 2021 }

  %0 Journal Article %1 tritscherfinancial %A Tritscher, Julian %A Krause, Anna %A Schl{\"o}r, Daniel %A Gwinner, Fabian %A von Mammen, Sebastian %A Hotho, Andreas %D 2021 %J IEE COG 2021 %T A financial game with opportunities for fraud %U https://ieee-cog.org/2021/assets/papers/paper_273.pdf %V 2021 %X Even though companies store large amounts of business data in enterprise resource planning (ERP) systems, obtaining data for financial fraud detection is prohibitively difficult due to privacy concerns and companies protecting trade secrets. One possible solution is game-based generation of synthetic ERP data, which poses the challenge of designing an environment that generates realistic ERP data and allows players to commit many different types of fraud. In this work, we design a multiplayer game that allows players to cooperatively run a fictional company, while simultaneously challenging them to maximize their personal gain. We introduce an approach for letting players explore fraud scenarios through emergent gameplay and present a prototype that may be primed with information from real world ERP systems to generate realistic data.
• 
  Semi-unsupervised Learning: An In-depth Parameter Analysis Davidson, Padraig; Buckermann, Florian; Steininger, Michael; Krause, Anna; Hotho, Andreas in KI 2021: Advances in Artificial Intelligence, S. Edelkamp, R. M{\"o}ller, E. Rueckert (eds.) (2021). 51–66.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  Creating datasets for supervised learning is a very challenging and expensive task, in which each input example has to be annotated with its expected output (e.g. object class). By combining unsupervised and semi-supervised learning, semi-unsupervised learning proposes a new paradigm for partially labeled datasets with additional unknown classes. In this paper we focus on a better understanding of this new learning paradigm and analyze the impact of the amount of labeled data, the number of augmented classes and the selection of hidden classes on the quality of prediction. Especially the number of augmented classes highly influences classification accuracy, which needs tuning for each dataset, since too few and too many augmented classes are detrimental to classifier performance. We also show that we can improve results on a large variety of datasets when using convolutional networks as feature extractors while applying output driven entropy regularization instead of a simple weight based L2 norm.

  @inproceedings{10.1007/978-3-030-87626-5_5, abstract = {Creating datasets for supervised learning is a very challenging and expensive task, in which each input example has to be annotated with its expected output (e.g. object class). By combining unsupervised and semi-supervised learning, semi-unsupervised learning proposes a new paradigm for partially labeled datasets with additional unknown classes. In this paper we focus on a better understanding of this new learning paradigm and analyze the impact of the amount of labeled data, the number of augmented classes and the selection of hidden classes on the quality of prediction. Especially the number of augmented classes highly influences classification accuracy, which needs tuning for each dataset, since too few and too many augmented classes are detrimental to classifier performance. We also show that we can improve results on a large variety of datasets when using convolutional networks as feature extractors while applying output driven entropy regularization instead of a simple weight based L2 norm.}, address = {Cham}, author = {Davidson, Padraig and Buckermann, Florian and Steininger, Michael and Krause, Anna and Hotho, Andreas}, booktitle = {KI 2021: Advances in Artificial Intelligence}, editor = {Edelkamp, Stefan and M{\"o}ller, Ralf and Rueckert, Elmar}, keywords = {unsupervised}, pages = {51–66}, publisher = {Springer International Publishing}, title = {Semi-unsupervised Learning: An In-depth Parameter Analysis}, year = 2021 }

  %0 Conference Paper %1 10.1007/978-3-030-87626-5_5 %A Davidson, Padraig %A Buckermann, Florian %A Steininger, Michael %A Krause, Anna %A Hotho, Andreas %B KI 2021: Advances in Artificial Intelligence %C Cham %D 2021 %E Edelkamp, Stefan %E M{\"o}ller, Ralf %E Rueckert, Elmar %I Springer International Publishing %P 51--66 %T Semi-unsupervised Learning: An In-depth Parameter Analysis %U https://link.springer.com/chapter/10.1007/978-3-030-87626-5_5 %X Creating datasets for supervised learning is a very challenging and expensive task, in which each input example has to be annotated with its expected output (e.g. object class). By combining unsupervised and semi-supervised learning, semi-unsupervised learning proposes a new paradigm for partially labeled datasets with additional unknown classes. In this paper we focus on a better understanding of this new learning paradigm and analyze the impact of the amount of labeled data, the number of augmented classes and the selection of hidden classes on the quality of prediction. Especially the number of augmented classes highly influences classification accuracy, which needs tuning for each dataset, since too few and too many augmented classes are detrimental to classifier performance. We also show that we can improve results on a large variety of datasets when using convolutional networks as feature extractors while applying output driven entropy regularization instead of a simple weight based L2 norm. %@ 978-3-030-87626-5

• 
  Integrating Keywords into BERT4Rec for Sequential Recommendation Fischer, Elisabeth; Zoller, Daniel; Dallmann, Alexander; Hotho, Andreas in KI 2020: Advances in Artificial Intelligence (2020).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{fischer2020integrating, author = {Fischer, Elisabeth and Zoller, Daniel and Dallmann, Alexander and Hotho, Andreas}, booktitle = {KI 2020: Advances in Artificial Intelligence}, keywords = {sequential}, title = {Integrating Keywords into BERT4Rec for Sequential Recommendation}, year = 2020 }

  %0 Conference Paper %1 fischer2020integrating %A Fischer, Elisabeth %A Zoller, Daniel %A Dallmann, Alexander %A Hotho, Andreas %B KI 2020: Advances in Artificial Intelligence %D 2020 %T Integrating Keywords into BERT4Rec for Sequential Recommendation
• 
  Financial Fraud Detection with Improved Neural Arithmetic Logic Units Schlör, Daniel; Ring, Markus; Krause, Anna; Hotho, Andreas (2020). (Vol. Fifth Workshop on MIning DAta for financial applicationS)
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @proceedings{schlr2020financial, author = {Schlör, Daniel and Ring, Markus and Krause, Anna and Hotho, Andreas}, keywords = {from:daschloer}, number = 5, title = {Financial Fraud Detection with Improved Neural Arithmetic Logic Units}, volume = {Fifth Workshop on MIning DAta for financial applicationS}, year = 2020 }

  %0 Conference Proceedings %1 schlr2020financial %A Schlör, Daniel %A Ring, Markus %A Krause, Anna %A Hotho, Andreas %D 2020 %N 5 %T Financial Fraud Detection with Improved Neural Arithmetic Logic Units %V Fifth Workshop on MIning DAta for financial applicationS
• 
  Evaluating the multi-task learning approach for land use regression modelling of air pollution Dulny, Andrzej; Steininger, Michael; Lautenschlager, Florian; Krause, Anna; Hotho, Andreas in International Conference on Frontiers of Artificial Intelligence and Machine Learning (2020).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.

  @inproceedings{dulny2020evaluating, abstract = {Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.}, author = {Dulny, Andrzej and Steininger, Michael and Lautenschlager, Florian and Krause, Anna and Hotho, Andreas}, booktitle = {International Conference on Frontiers of Artificial Intelligence and Machine Learning}, keywords = {myown}, organization = {IASED}, title = {Evaluating the multi-task learning approach for land use regression modelling of air pollution}, year = 2020 }

  %0 Conference Paper %1 dulny2020evaluating %A Dulny, Andrzej %A Steininger, Michael %A Lautenschlager, Florian %A Krause, Anna %A Hotho, Andreas %B International Conference on Frontiers of Artificial Intelligence and Machine Learning %D 2020 %T Evaluating the multi-task learning approach for land use regression modelling of air pollution %X Air pollution has been linked to several health problems including heart disease, stroke and lung cancer. Modelling and analyzing this dependency requires reliable and accurate air pollutant measurements collected by stationary air monitoring stations. However, usually only a low number of such stations are present within a single city. To retrieve pollution concentrations for unmeasured locations, researchers rely on land use regression (LUR) models. Those models are typically developed for one pollutant only. However, as results in different areas have shown, modelling several related output variables through multi-task learning can improve the prediction results of the models significantly. In this work, we compared prediction results from single-task and multi-task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset. LUR features were generated from OpenStreetMap using OpenLUR and used to train hard parameter sharing multilayer perceptron models. The results show multi-task learning with sufficient data significantly improves the performance of a LUR model.
• 
  iNALU: Improved Neural Arithmetic Logic Unit Schlör, Daniel; Ring, Markus; Hotho, Andreas in Frontiers in Artificial Intelligence (2020). 3 71.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. Although NALUs have been shown to perform well on various downstream tasks, an in-depth analysis reveals practical shortcomings by design, such as the inability to multiply or divide negative input values or training stability issues for deeper networks. We address these issues and propose an improved model architecture. We evaluate our model empirically in various settings from learning basic arithmetic operations to more complex functions. Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.

  @article{10.3389/frai.2020.00071, abstract = {Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. Although NALUs have been shown to perform well on various downstream tasks, an in-depth analysis reveals practical shortcomings by design, such as the inability to multiply or divide negative input values or training stability issues for deeper networks. We address these issues and propose an improved model architecture. We evaluate our model empirically in various settings from learning basic arithmetic operations to more complex functions. Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.}, author = {Schlör, Daniel and Ring, Markus and Hotho, Andreas}, journal = {Frontiers in Artificial Intelligence}, keywords = {networks}, pages = 71, title = {iNALU: Improved Neural Arithmetic Logic Unit}, volume = 3, year = 2020 }

  %0 Journal Article %1 10.3389/frai.2020.00071 %A Schlör, Daniel %A Ring, Markus %A Hotho, Andreas %D 2020 %J Frontiers in Artificial Intelligence %P 71 %R 10.3389/frai.2020.00071 %T iNALU: Improved Neural Arithmetic Logic Unit %U https://www.frontiersin.org/article/10.3389/frai.2020.00071 %V 3 %X Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. Although NALUs have been shown to perform well on various downstream tasks, an in-depth analysis reveals practical shortcomings by design, such as the inability to multiply or divide negative input values or training stability issues for deeper networks. We address these issues and propose an improved model architecture. We evaluate our model empirically in various settings from learning basic arithmetic operations to more complex functions. Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.
• 
  Where to Submit? Helping Researchers to Choose the Right Venue Kobs, Konstantin; Koopmann, Tobias; Zehe, Albin; Fernes, David; Krop, Philipp; Hotho, Andreas in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings (2020). 878–883.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{kobs-etal-2020-submit, address = {Online}, author = {Kobs, Konstantin and Koopmann, Tobias and Zehe, Albin and Fernes, David and Krop, Philipp and Hotho, Andreas}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings}, keywords = {from:konstantinkobs}, month = {nov}, pages = {878–883}, publisher = {Association for Computational Linguistics}, title = {Where to Submit? Helping Researchers to Choose the Right Venue}, year = 2020 }

  %0 Conference Paper %1 kobs-etal-2020-submit %A Kobs, Konstantin %A Koopmann, Tobias %A Zehe, Albin %A Fernes, David %A Krop, Philipp %A Hotho, Andreas %B Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings %C Online %D 2020 %I Association for Computational Linguistics %P 878--883 %T Where to Submit? Helping Researchers to Choose the Right Venue %U https://www.aclweb.org/anthology/2020.findings-emnlp.78
• 
  Towards Predicting the Subscription Status of Twitch.tv Users Kobs, Konstantin; Potthast, Martin; Wiegmann, Matti; Zehe, Albin; Stein, Benno; Hotho, Andreas in Proceedings of ECML-PKDD 2020 ChAT Discovery Challenge on Chat Analytics for Twitch (2020).
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{kobstowards, author = {Kobs, Konstantin and Potthast, Martin and Wiegmann, Matti and Zehe, Albin and Stein, Benno and Hotho, Andreas}, journal = {Proceedings of ECML-PKDD 2020 ChAT Discovery Challenge on Chat Analytics for Twitch}, keywords = {twitch}, title = {Towards Predicting the Subscription Status of Twitch.tv Users}, year = 2020 }

  %0 Journal Article %1 kobstowards %A Kobs, Konstantin %A Potthast, Martin %A Wiegmann, Matti %A Zehe, Albin %A Stein, Benno %A Hotho, Andreas %D 2020 %J Proceedings of ECML-PKDD 2020 ChAT Discovery Challenge on Chat Analytics for Twitch %T Towards Predicting the Subscription Status of Twitch.tv Users %U http://ceur-ws.org/Vol-2661/paper1.pdf
• 
  Deep Learning for Climate Model Output Statistics Steininger, Michael; Abel, Daniel; Ziegler, Katrin; Krause, Anna; Paeth, Heiko; Hotho, Andreas in Tackling Climate Change with Machine Learning Workshop at NeurIPS 2020 (2020).
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{steininger2020deep, author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas}, journal = {Tackling Climate Change with Machine Learning Workshop at NeurIPS 2020}, keywords = {from:msteininger}, title = {Deep Learning for Climate Model Output Statistics}, year = 2020 }

  %0 Journal Article %1 steininger2020deep %A Steininger, Michael %A Abel, Daniel %A Ziegler, Katrin %A Krause, Anna %A Paeth, Heiko %A Hotho, Andreas %D 2020 %J Tackling Climate Change with Machine Learning Workshop at NeurIPS 2020 %T Deep Learning for Climate Model Output Statistics %U https://www.climatechange.ai/papers/neurips2020/7
• 
  Evaluation of Post-hoc XAI Approaches Through Synthetic Tabular Data Tritscher, Julian; Ring, Markus; Schlr, Daniel; Hettinger, Lena; Hotho, Andreas in Foundations of Intelligent Systems, D. Helic, G. Leitner, M. Stettinger, A. Felfernig, Z. W. Ra{\’{s}} (eds.) (2020). 422–430.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data.

  @inproceedings{tritscher2020evaluation, abstract = {Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data.}, address = {Cham}, author = {Tritscher, Julian and Ring, Markus and Schlr, Daniel and Hettinger, Lena and Hotho, Andreas}, booktitle = {Foundations of Intelligent Systems}, editor = {Helic, Denis and Leitner, Gerhard and Stettinger, Martin and Felfernig, Alexander and Ra{\'{s}}, Zbigniew W.}, keywords = {from:hotho}, pages = {422–430}, publisher = {Springer International Publishing}, title = {Evaluation of Post-hoc XAI Approaches Through Synthetic Tabular Data}, year = 2020 }

  %0 Conference Paper %1 tritscher2020evaluation %A Tritscher, Julian %A Ring, Markus %A Schlr, Daniel %A Hettinger, Lena %A Hotho, Andreas %B Foundations of Intelligent Systems %C Cham %D 2020 %E Helic, Denis %E Leitner, Gerhard %E Stettinger, Martin %E Felfernig, Alexander %E Ra{\'{s}}, Zbigniew W. %I Springer International Publishing %P 422--430 %T Evaluation of Post-hoc XAI Approaches Through Synthetic Tabular Data %X Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data. %@ 978-3-030-59491-6
• 
  Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part I Brefeld, Ulf; Fromont, Élisa; Hotho, Andreas; Knobbe, Arno J.; Maathuis, Marloes H.; Robardet, Céline in Lecture Notes in Computer Science (2020). (Vol. 11906) Springer.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @proceedings{brefeld2020machine3, booktitle = {ECML/PKDD (1)}, editor = {Brefeld, Ulf and Fromont, Élisa and Hotho, Andreas and Knobbe, Arno J. and Maathuis, Marloes H. and Robardet, Céline}, keywords = {from:hotho}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part I}, volume = 11906, year = 2020 }

  %0 Conference Proceedings %1 brefeld2020machine3 %B ECML/PKDD (1) %D 2020 %E Brefeld, Ulf %E Fromont, Élisa %E Hotho, Andreas %E Knobbe, Arno J. %E Maathuis, Marloes H. %E Robardet, Céline %I Springer %T Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part I %U http://dblp.uni-trier.de/db/conf/pkdd/pkdd2019-1.html %V 11906 %@ 978-3-030-46150-8
• 
  Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part III Brefeld, Ulf; Fromont, Élisa; Hotho, Andreas; Knobbe, Arno J.; Maathuis, Marloes H.; Robardet, Céline in Lecture Notes in Computer Science (2020). (Vol. 11908) Springer.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @proceedings{brefeld2020machine1, booktitle = {ECML/PKDD (3)}, editor = {Brefeld, Ulf and Fromont, Élisa and Hotho, Andreas and Knobbe, Arno J. and Maathuis, Marloes H. and Robardet, Céline}, keywords = {from:hotho}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part III}, volume = 11908, year = 2020 }

  %0 Conference Proceedings %1 brefeld2020machine1 %B ECML/PKDD (3) %D 2020 %E Brefeld, Ulf %E Fromont, Élisa %E Hotho, Andreas %E Knobbe, Arno J. %E Maathuis, Marloes H. %E Robardet, Céline %I Springer %T Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part III %U http://dblp.uni-trier.de/db/conf/pkdd/pkdd2019-3.html %V 11908 %@ 978-3-030-46133-1
• 
  Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part II Brefeld, Ulf; Fromont, Élisa; Hotho, Andreas; Knobbe, Arno J.; Maathuis, Marloes H.; Robardet, Céline in Lecture Notes in Computer Science (2020). (Vol. 11907) Springer.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @proceedings{brefeld2020machine2, booktitle = {ECML/PKDD (2)}, editor = {Brefeld, Ulf and Fromont, Élisa and Hotho, Andreas and Knobbe, Arno J. and Maathuis, Marloes H. and Robardet, Céline}, keywords = {from:hotho}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part II}, volume = 11907, year = 2020 }

  %0 Conference Proceedings %1 brefeld2020machine2 %B ECML/PKDD (2) %D 2020 %E Brefeld, Ulf %E Fromont, Élisa %E Hotho, Andreas %E Knobbe, Arno J. %E Maathuis, Marloes H. %E Robardet, Céline %I Springer %T Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part II %U http://dblp.uni-trier.de/db/conf/pkdd/pkdd2019-2.html %V 11907 %@ 978-3-030-46147-8
• 
  NICER — Aesthetic Image Enhancement with Humans in the Loop Fischer, Michael; Kobs, Konstantin; Hotho, Andreas in ACHI 2020: The Thirteenth International Conference on Advances in Computer-Human Interactions (2020). 357–362.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Fully- or semi-automatic image enhancement software helps users to increase the visual appeal of photos and does not require in-depth knowledge of manual image editing. However, fully-automatic approaches usually enhance the image in a black-box manner that does not give the user any control over the optimization process, possibly leading to edited images that do not subjectively appeal to the user. Semi-automatic methods mostly allow for controlling which pre-defined editing step is taken, which restricts the users in their creativity and ability to make detailed adjustments, such as brightness or contrast. We argue that incorporating user preferences by guiding an automated enhancement method simplifies image editing and increases the enhancement’s focus on the user. This work thus proposes the Neural Image Correction & Enhancement Routine (NICER), a neural network based approach to no-reference image enhancement in a fully-, semi-automatic or fully manual process that is interactive and user-centered. NICER iteratively adjusts image editing parameters in order to maximize an aesthetic score based on image style and content. Users can modify these parameters at any time and guide the optimization process towards a desired direction. This interactive workflow is a novelty in the field of human-computer interaction for image enhancement tasks. In a user study, we show that NICER can improve image aesthetics without user interaction and that allowing user interaction leads to diverse enhancement outcomes that are strongly preferred over the unedited image. We make our code publicly available to facilitate further research in this direction.

  @inproceedings{fischer2020nicer, abstract = {Fully- or semi-automatic image enhancement software helps users to increase the visual appeal of photos and does not require in-depth knowledge of manual image editing. However, fully-automatic approaches usually enhance the image in a black-box manner that does not give the user any control over the optimization process, possibly leading to edited images that do not subjectively appeal to the user. Semi-automatic methods mostly allow for controlling which pre-defined editing step is taken, which restricts the users in their creativity and ability to make detailed adjustments, such as brightness or contrast. We argue that incorporating user preferences by guiding an automated enhancement method simplifies image editing and increases the enhancement’s focus on the user. This work thus proposes the Neural Image Correction & Enhancement Routine (NICER), a neural network based approach to no-reference image enhancement in a fully-, semi-automatic or fully manual process that is interactive and user-centered. NICER iteratively adjusts image editing parameters in order to maximize an aesthetic score based on image style and content. Users can modify these parameters at any time and guide the optimization process towards a desired direction. This interactive workflow is a novelty in the field of human-computer interaction for image enhancement tasks. In a user study, we show that NICER can improve image aesthetics without user interaction and that allowing user interaction leads to diverse enhancement outcomes that are strongly preferred over the unedited image. We make our code publicly available to facilitate further research in this direction.}, author = {Fischer, Michael and Kobs, Konstantin and Hotho, Andreas}, journal = {ACHI 2020: The Thirteenth International Conference on Advances in Computer-Human Interactions}, keywords = {from:konstantinkobs}, pages = {357-362}, title = {NICER — Aesthetic Image Enhancement with Humans in the Loop}, year = 2020 }

  %0 Conference Paper %1 fischer2020nicer %A Fischer, Michael %A Kobs, Konstantin %A Hotho, Andreas %D 2020 %J ACHI 2020: The Thirteenth International Conference on Advances in Computer-Human Interactions %P 357-362 %T NICER — Aesthetic Image Enhancement with Humans in the Loop %X Fully- or semi-automatic image enhancement software helps users to increase the visual appeal of photos and does not require in-depth knowledge of manual image editing. However, fully-automatic approaches usually enhance the image in a black-box manner that does not give the user any control over the optimization process, possibly leading to edited images that do not subjectively appeal to the user. Semi-automatic methods mostly allow for controlling which pre-defined editing step is taken, which restricts the users in their creativity and ability to make detailed adjustments, such as brightness or contrast. We argue that incorporating user preferences by guiding an automated enhancement method simplifies image editing and increases the enhancement’s focus on the user. This work thus proposes the Neural Image Correction & Enhancement Routine (NICER), a neural network based approach to no-reference image enhancement in a fully-, semi-automatic or fully manual process that is interactive and user-centered. NICER iteratively adjusts image editing parameters in order to maximize an aesthetic score based on image style and content. Users can modify these parameters at any time and guide the optimization process towards a desired direction. This interactive workflow is a novelty in the field of human-computer interaction for image enhancement tasks. In a user study, we show that NICER can improve image aesthetics without user interaction and that allowing user interaction leads to diverse enhancement outcomes that are strongly preferred over the unedited image. We make our code publicly available to facilitate further research in this direction. %@ 978-1-61208-761-0
• 
  Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels Kobs, Konstantin; Zehe, Albin; Bernstetter, Armin; Chibane, Julian; Pfister, Jan; Tritscher, Julian; Hotho, Andreas in ACM Transactions on Social Computing (2020).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{kobs2020emotecontrolled, author = {Kobs, Konstantin and Zehe, Albin and Bernstetter, Armin and Chibane, Julian and Pfister, Jan and Tritscher, Julian and Hotho, Andreas}, journal = {ACM Transactions on Social Computing}, keywords = {twitch}, title = {Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels}, year = 2020 }

  %0 Journal Article %1 kobs2020emotecontrolled %A Kobs, Konstantin %A Zehe, Albin %A Bernstetter, Armin %A Chibane, Julian %A Pfister, Jan %A Tritscher, Julian %A Hotho, Andreas %D 2020 %J ACM Transactions on Social Computing %R 10.1145/3365523 %T Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels
• 
  Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels Kobs, Konstantin; Zehe, Albin; Bernstetter, Armin; Chibane, Julian; Pfister, Jan; Tritscher, Julian; Hotho, Andreas in {ACM} Transactions on Social Computing (2020). 3(2) 1–34.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{Kobs_2020, author = {Kobs, Konstantin and Zehe, Albin and Bernstetter, Armin and Chibane, Julian and Pfister, Jan and Tritscher, Julian and Hotho, Andreas}, journal = {{ACM} Transactions on Social Computing}, keywords = {twitch}, month = {may}, number = 2, pages = {1–34}, publisher = {Association for Computing Machinery ({ACM})}, title = {Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels}, volume = 3, year = 2020 }

  %0 Journal Article %1 Kobs_2020 %A Kobs, Konstantin %A Zehe, Albin %A Bernstetter, Armin %A Chibane, Julian %A Pfister, Jan %A Tritscher, Julian %A Hotho, Andreas %D 2020 %I Association for Computing Machinery ({ACM}) %J {ACM} Transactions on Social Computing %N 2 %P 1--34 %R 10.1145/3365523 %T Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels %U https://doi.org/10.1145%2F3365523 %V 3
• 
  Improving Sentiment Analysis with Biofeedback Data Schl{\"o}r, Daniel; Zehe, Albin; Kobs, Konstantin; Veseli, Blerta; Westermeier, Franziska; Br{\"u}bach, Larissa; Roth, Daniel; Latoschik, Marc Erich; Hotho, Andreas in Proceedings of LREC2020 Workshop ``People in language, vision and the mind’’ (ONION2020) (2020). 28–33.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level.

  @inproceedings{schlor-etal-2020-improving, abstract = {Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level.}, address = {Marseille, France}, author = {Schl{\"o}r, Daniel and Zehe, Albin and Kobs, Konstantin and Veseli, Blerta and Westermeier, Franziska and Br{\"u}bach, Larissa and Roth, Daniel and Latoschik, Marc Erich and Hotho, Andreas}, booktitle = {Proceedings of LREC2020 Workshop ``People in language, vision and the mind'' (ONION2020)}, keywords = {from:albinzehe}, month = {may}, pages = {28–33}, publisher = {European Language Resources Association (ELRA)}, title = {Improving Sentiment Analysis with Biofeedback Data}, year = 2020 }

  %0 Conference Paper %1 schlor-etal-2020-improving %A Schl{\"o}r, Daniel %A Zehe, Albin %A Kobs, Konstantin %A Veseli, Blerta %A Westermeier, Franziska %A Br{\"u}bach, Larissa %A Roth, Daniel %A Latoschik, Marc Erich %A Hotho, Andreas %B Proceedings of LREC2020 Workshop ``People in language, vision and the mind'' (ONION2020) %C Marseille, France %D 2020 %I European Language Resources Association (ELRA) %P 28--33 %T Improving Sentiment Analysis with Biofeedback Data %U https://www.aclweb.org/anthology/2020.onion-1.5 %X Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level. %@ 979-10-95546-70-2
• 
  LM4KG: Improving Common Sense Knowledge Graphs with Language Models Omeliyanenko, Janna; Zehe, Albin; Hettinger, Lena; Hotho, Andreas in International Semantic Web Conference (2020).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{omeliyanenko2020reweight, author = {Omeliyanenko, Janna and Zehe, Albin and Hettinger, Lena and Hotho, Andreas}, booktitle = {International Semantic Web Conference}, keywords = {from:schwemmlein}, organization = {Springer}, title = {LM4KG: Improving Common Sense Knowledge Graphs with Language Models}, year = 2020 }

  %0 Conference Paper %1 omeliyanenko2020reweight %A Omeliyanenko, Janna %A Zehe, Albin %A Hettinger, Lena %A Hotho, Andreas %B International Semantic Web Conference %D 2020 %T LM4KG: Improving Common Sense Knowledge Graphs with Language Models
• 
  Evaluation of post-hoc XAI approaches through synthetic tabular data Tritscher, Julian; Ring, Markus; Schlör, Daniel; Hettinger, Lena; Hotho, Andreas in International Symposium on Methodologies for Intelligent Systems (2020).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data.

  @article{tritscher2020evaluation, abstract = {Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data.}, author = {Tritscher, Julian and Ring, Markus and Schlör, Daniel and Hettinger, Lena and Hotho, Andreas}, booktitle = {International Symposium on Methodologies for Intelligent Systems}, keywords = {from:tritsch}, note = {Accepted but not published}, organization = {Springer}, title = {Evaluation of post-hoc XAI approaches through synthetic tabular data}, year = 2020 }

  %0 Journal Article %1 tritscher2020evaluation %A Tritscher, Julian %A Ring, Markus %A Schlör, Daniel %A Hettinger, Lena %A Hotho, Andreas %B International Symposium on Methodologies for Intelligent Systems %D 2020 %T Evaluation of post-hoc XAI approaches through synthetic tabular data %X Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data.
• 
  SimLoss: Class Similarities in Cross Entropy Kobs, Konstantin; Steininger, Michael; Zehe, Albin; Lautenschlager, Florian; Hotho, Andreas (2020).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a rose as "violet" is better than as "truck". We introduce SimLoss, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge. We test SimLoss on Age Estimation and Image Classification and find that it brings significant improvements over CCE on several metrics. SimLoss therefore allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same. Code and additional resources can be found at https://github.com/konstantinkobs/SimLoss.

  @misc{kobs2020simloss, abstract = {One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a rose as "violet" is better than as "truck". We introduce SimLoss, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge. We test SimLoss on Age Estimation and Image Classification and find that it brings significant improvements over CCE on several metrics. SimLoss therefore allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same. Code and additional resources can be found at https://github.com/konstantinkobs/SimLoss.}, author = {Kobs, Konstantin and Steininger, Michael and Zehe, Albin and Lautenschlager, Florian and Hotho, Andreas}, keywords = {myown}, note = {cite arxiv:2003.03182Comment: This paper is going to be published in the proceedings of the 25th International Symposium on Methodologies for Intelligent Systems (ISMIS)}, title = {SimLoss: Class Similarities in Cross Entropy}, year = 2020 }

  %0 Generic %1 kobs2020simloss %A Kobs, Konstantin %A Steininger, Michael %A Zehe, Albin %A Lautenschlager, Florian %A Hotho, Andreas %D 2020 %T SimLoss: Class Similarities in Cross Entropy %U http://arxiv.org/abs/2003.03182 %X One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a rose as "violet" is better than as "truck". We introduce SimLoss, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge. We test SimLoss on Age Estimation and Image Classification and find that it brings significant improvements over CCE on several metrics. SimLoss therefore allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same. Code and additional resources can be found at https://github.com/konstantinkobs/SimLoss.
• 
  MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images Steininger, Michael; Kobs, Konstantin; Zehe, Albin; Lautenschlager, Florian; Becker, Martin; Hotho, Andreas in ACM Trans. Spatial Algorithms Syst. (2020). 6(3)
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Land-use regression (LUR) models are important for the assessment of air pollution concentrations in areas without measurement stations. While many such models exist, they often use manually constructed features based on restricted, locally available data. Thus, they are typically hard to reproduce and challenging to adapt to areas beyond those they have been developed for. In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data. Progress within this paradigm will alleviate the need for experts to adapt models to the local characteristics of the available data sources and thus facilitate the generalizability of air pollution models to new areas on a global scale. In order to illustrate the feasibility of the DOG paradigm for LUR, we introduce a deep learning model called MapLUR. It is based on a convolutional neural network architecture and is trained exclusively on globally and openly available map data without requiring manual feature engineering. We compare our model to state-of-the-art baselines like linear regression, random forests and multi-layer perceptrons using a large data set of modeled NO2 concentrations in Central London. Our results show that MapLUR significantly outperforms these approaches even though they are provided with manually tailored features. Furthermore, we illustrate that the automatic feature extraction inherent to models based on the DOG paradigm can learn features that are readily interpretable and closely resemble those commonly used in traditional LUR approaches.

  @article{10.1145/3380973, abstract = {Land-use regression (LUR) models are important for the assessment of air pollution concentrations in areas without measurement stations. While many such models exist, they often use manually constructed features based on restricted, locally available data. Thus, they are typically hard to reproduce and challenging to adapt to areas beyond those they have been developed for. In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data. Progress within this paradigm will alleviate the need for experts to adapt models to the local characteristics of the available data sources and thus facilitate the generalizability of air pollution models to new areas on a global scale. In order to illustrate the feasibility of the DOG paradigm for LUR, we introduce a deep learning model called MapLUR. It is based on a convolutional neural network architecture and is trained exclusively on globally and openly available map data without requiring manual feature engineering. We compare our model to state-of-the-art baselines like linear regression, random forests and multi-layer perceptrons using a large data set of modeled NO2 concentrations in Central London. Our results show that MapLUR significantly outperforms these approaches even though they are provided with manually tailored features. Furthermore, we illustrate that the automatic feature extraction inherent to models based on the DOG paradigm can learn features that are readily interpretable and closely resemble those commonly used in traditional LUR approaches.}, address = {New York, NY, USA}, author = {Steininger, Michael and Kobs, Konstantin and Zehe, Albin and Lautenschlager, Florian and Becker, Martin and Hotho, Andreas}, journal = {ACM Trans. Spatial Algorithms Syst.}, keywords = {from:msteininger}, month = {apr}, number = 3, publisher = {Association for Computing Machinery}, title = {MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images}, volume = 6, year = 2020 }

  %0 Journal Article %1 10.1145/3380973 %A Steininger, Michael %A Kobs, Konstantin %A Zehe, Albin %A Lautenschlager, Florian %A Becker, Martin %A Hotho, Andreas %C New York, NY, USA %D 2020 %I Association for Computing Machinery %J ACM Trans. Spatial Algorithms Syst. %N 3 %R 10.1145/3380973 %T MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images %U https://doi.org/10.1145/3380973 %V 6 %X Land-use regression (LUR) models are important for the assessment of air pollution concentrations in areas without measurement stations. While many such models exist, they often use manually constructed features based on restricted, locally available data. Thus, they are typically hard to reproduce and challenging to adapt to areas beyond those they have been developed for. In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data. Progress within this paradigm will alleviate the need for experts to adapt models to the local characteristics of the available data sources and thus facilitate the generalizability of air pollution models to new areas on a global scale. In order to illustrate the feasibility of the DOG paradigm for LUR, we introduce a deep learning model called MapLUR. It is based on a convolutional neural network architecture and is trained exclusively on globally and openly available map data without requiring manual feature engineering. We compare our model to state-of-the-art baselines like linear regression, random forests and multi-layer perceptrons using a large data set of modeled NO2 concentrations in Central London. Our results show that MapLUR significantly outperforms these approaches even though they are provided with manually tailored features. Furthermore, we illustrate that the automatic feature extraction inherent to models based on the DOG paradigm can learn features that are readily interpretable and closely resemble those commonly used in traditional LUR approaches.
• 
  OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning Lautenschlager, Florian; Becker, Martin; Kobs, Konstantin; Steininger, Michael; Davidson, Padraig; Krause, Anna; Hotho, Andreas in Atmospheric Environment (2020). 233 117535.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.

  @article{lautenschlager2020openlur, abstract = {To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.}, author = {Lautenschlager, Florian and Becker, Martin and Kobs, Konstantin and Steininger, Michael and Davidson, Padraig and Krause, Anna and Hotho, Andreas}, journal = {Atmospheric Environment}, keywords = {from:lautenschlager}, month = {July}, pages = 117535, title = {OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning}, volume = 233, year = 2020 }

  %0 Journal Article %1 lautenschlager2020openlur %A Lautenschlager, Florian %A Becker, Martin %A Kobs, Konstantin %A Steininger, Michael %A Davidson, Padraig %A Krause, Anna %A Hotho, Andreas %D 2020 %J Atmospheric Environment %P 117535 %R https://doi.org/10.1016/j.atmosenv.2020.117535 %T OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning %U http://www.sciencedirect.com/science/article/pii/S1352231020302703 %V 233 %X To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.
• 
  HarryMotions – Classifying Relationships in Harry Potter based on Emotion Analysis Zehe, Albin; Arns, Julia; Hettinger, Lena; Hotho, Andreas in 5th SwissText & 16th KONVENS Joint Conference (2020).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{zehe2020harrymotions, author = {Zehe, Albin and Arns, Julia and Hettinger, Lena and Hotho, Andreas}, booktitle = {5th SwissText & 16th KONVENS Joint Conference}, keywords = {from:albinzehe}, title = {HarryMotions – Classifying Relationships in Harry Potter based on Emotion Analysis}, year = 2020 }

  %0 Conference Paper %1 zehe2020harrymotions %A Zehe, Albin %A Arns, Julia %A Hettinger, Lena %A Hotho, Andreas %B 5th SwissText & 16th KONVENS Joint Conference %D 2020 %T HarryMotions – Classifying Relationships in Harry Potter based on Emotion Analysis
• 
  Anomaly Detection in Beehives using Deep Recurrent Autoencoders Davidson, Padraig; Steininger, Michael; Lautenschlager, Florian; Kobs, Konstantin; Krause, Anna; Hotho, Andreas in Proceedings of the 9th International Conference on Sensor Networks (SENSORNETS 2020) (2020). 142–149.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{davidson2020anomaly, author = {Davidson, Padraig and Steininger, Michael and Lautenschlager, Florian and Kobs, Konstantin and Krause, Anna and Hotho, Andreas}, booktitle = {Proceedings of the 9th International Conference on Sensor Networks (SENSORNETS 2020)}, keywords = {from:pdavidson}, number = 9, pages = {142-149}, publisher = {SCITEPRESS – Science and Technology Publications, Lda.}, title = {Anomaly Detection in Beehives using Deep Recurrent Autoencoders}, year = 2020 }

  %0 Conference Paper %1 davidson2020anomaly %A Davidson, Padraig %A Steininger, Michael %A Lautenschlager, Florian %A Kobs, Konstantin %A Krause, Anna %A Hotho, Andreas %B Proceedings of the 9th International Conference on Sensor Networks (SENSORNETS 2020) %D 2020 %I SCITEPRESS – Science and Technology Publications, Lda. %N 9 %P 142-149 %T Anomaly Detection in Beehives using Deep Recurrent Autoencoders
• 
  Time Series Forecasting for Self-Aware Systems {Bauer}, A.; {Züfle}, M.; {Herbst}, N.; {Zehe}, A.; {Hotho}, A.; {Kounev}, S. in Proceedings of the IEEE (2020). 1–26.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  Modern distributed systems and Internet-of-Things applications are governed by fast living and changing requirements. Moreover, they have to struggle with huge amounts of data that they create or have to process. To improve the self-awareness of such systems and enable proactive and autonomous decisions, reliable time series forecasting methods are required. However, selecting a suitable forecasting method for a given scenario is a challenging task. According to the ``No-Free-Lunch Theorem,'' there is no general forecasting method that always performs best. Thus, manual feature engineering remains to be a mandatory expert task to avoid trial and error. Furthermore, determining the expected time-to-result of existing forecasting methods is a challenge. In this article, we extensively assess the state-of-the-art in time series forecasting. We compare existing methods and discuss the issues that have to be addressed to enable their use in a self-aware computing context. To address these issues, we present a step-by-step approach to fully automate the feature engineering and forecasting process. Then, following the principles from benchmarking, we establish a level-playing field for evaluating the accuracy and time-to-result of automated forecasting methods for a broad set of application scenarios. We provide results of a benchmarking competition to guide in selecting and appropriately using existing forecasting methods for a given self-aware computing context. Finally, we present a case study in the area of self-aware data-center resource management to exemplify the benefits of fully automated learning and reasoning processes on time series data.

  @article{9069193, abstract = {Modern distributed systems and Internet-of-Things applications are governed by fast living and changing requirements. Moreover, they have to struggle with huge amounts of data that they create or have to process. To improve the self-awareness of such systems and enable proactive and autonomous decisions, reliable time series forecasting methods are required. However, selecting a suitable forecasting method for a given scenario is a challenging task. According to the ``No-Free-Lunch Theorem,'' there is no general forecasting method that always performs best. Thus, manual feature engineering remains to be a mandatory expert task to avoid trial and error. Furthermore, determining the expected time-to-result of existing forecasting methods is a challenge. In this article, we extensively assess the state-of-the-art in time series forecasting. We compare existing methods and discuss the issues that have to be addressed to enable their use in a self-aware computing context. To address these issues, we present a step-by-step approach to fully automate the feature engineering and forecasting process. Then, following the principles from benchmarking, we establish a level-playing field for evaluating the accuracy and time-to-result of automated forecasting methods for a broad set of application scenarios. We provide results of a benchmarking competition to guide in selecting and appropriately using existing forecasting methods for a given self-aware computing context. Finally, we present a case study in the area of self-aware data-center resource management to exemplify the benefits of fully automated learning and reasoning processes on time series data.}, author = {{Bauer}, A. and {Züfle}, M. and {Herbst}, N. and {Zehe}, A. and {Hotho}, A. and {Kounev}, S.}, journal = {Proceedings of the IEEE}, keywords = {from:albinzehe}, pages = {1-26}, title = {Time Series Forecasting for Self-Aware Systems}, year = 2020 }

  %0 Journal Article %1 9069193 %A {Bauer}, A. %A {Züfle}, M. %A {Herbst}, N. %A {Zehe}, A. %A {Hotho}, A. %A {Kounev}, S. %D 2020 %J Proceedings of the IEEE %P 1-26 %R 10.1109/JPROC.2020.2983857 %T Time Series Forecasting for Self-Aware Systems %X Modern distributed systems and Internet-of-Things applications are governed by fast living and changing requirements. Moreover, they have to struggle with huge amounts of data that they create or have to process. To improve the self-awareness of such systems and enable proactive and autonomous decisions, reliable time series forecasting methods are required. However, selecting a suitable forecasting method for a given scenario is a challenging task. According to the ``No-Free-Lunch Theorem,'' there is no general forecasting method that always performs best. Thus, manual feature engineering remains to be a mandatory expert task to avoid trial and error. Furthermore, determining the expected time-to-result of existing forecasting methods is a challenge. In this article, we extensively assess the state-of-the-art in time series forecasting. We compare existing methods and discuss the issues that have to be addressed to enable their use in a self-aware computing context. To address these issues, we present a step-by-step approach to fully automate the feature engineering and forecasting process. Then, following the principles from benchmarking, we establish a level-playing field for evaluating the accuracy and time-to-result of automated forecasting methods for a broad set of application scenarios. We provide results of a benchmarking competition to guide in selecting and appropriately using existing forecasting methods for a given self-aware computing context. Finally, we present a case study in the area of self-aware data-center resource management to exemplify the benefits of fully automated learning and reasoning processes on time series data.
• 
  Smartwatch-Derived Data and Machine Learning Algorithms Estimate Classes of Ratings of Perceived Exertion in Runners: A Pilot Study Davidson, Padraig; Düking, Peter; Zinner, Christoph; Sperlich, Billy; Hotho, Andreas in Sensors (2020).
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{davidson2020smartwatchderived, author = {Davidson, Padraig and Düking, Peter and Zinner, Christoph and Sperlich, Billy and Hotho, Andreas}, journal = {Sensors}, keywords = {from:pdavidson}, month = {may}, title = {Smartwatch-Derived Data and Machine Learning Algorithms Estimate Classes of Ratings of Perceived Exertion in Runners: A Pilot Study}, year = 2020 }

  %0 Journal Article %1 davidson2020smartwatchderived %A Davidson, Padraig %A Düking, Peter %A Zinner, Christoph %A Sperlich, Billy %A Hotho, Andreas %D 2020 %J Sensors %R 10.3390/s20092637 %T Smartwatch-Derived Data and Machine Learning Algorithms Estimate Classes of Ratings of Perceived Exertion in Runners: A Pilot Study %U https://www.mdpi.com/1424-8220/20/9/2637
• 
  Improving Sentiment Analysis with Biofeedback Data Schlör, Daniel; Zehe, Albin; Kobs, Konstantin; Veseli, Blerta; Westermeier, Franziska; Brübach, Larissa; Roth, Daniel; Latoschik, Marc Erich; Hotho, Andreas in Proceedings of the Workshop on peOple in laNguage, vIsiOn and the miNd (ONION) (2020).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level.

  @inproceedings{schlor2020improving, abstract = {Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level.}, author = {Schlör, Daniel and Zehe, Albin and Kobs, Konstantin and Veseli, Blerta and Westermeier, Franziska and Brübach, Larissa and Roth, Daniel and Latoschik, Marc Erich and Hotho, Andreas}, booktitle = {Proceedings of the Workshop on peOple in laNguage, vIsiOn and the miNd (ONION)}, keywords = {from:konstantinkobs}, title = {Improving Sentiment Analysis with Biofeedback Data}, year = 2020 }

  %0 Conference Paper %1 schlor2020improving %A Schlör, Daniel %A Zehe, Albin %A Kobs, Konstantin %A Veseli, Blerta %A Westermeier, Franziska %A Brübach, Larissa %A Roth, Daniel %A Latoschik, Marc Erich %A Hotho, Andreas %B Proceedings of the Workshop on peOple in laNguage, vIsiOn and the miNd (ONION) %D 2020 %T Improving Sentiment Analysis with Biofeedback Data %U https://downloads.hci.informatik.uni-wuerzburg.de/2018-ieeevr-lugrin-vr-teacher-training/2020-onion-sentiment-eeg-preprint.pdf %X Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a subtle manner, and are highly depending on context. For example, machine learning approaches for text-based sentiment analysis often rely on incorporating sentiment lexicons or language models to capture the contextual meaning. This paper explores if and how we further can enhance sentiment analysis using biofeedback of humans which are experiencing emotions while reading texts. Specifically, we record the heart rate and brain waves of readers that are presented with short texts which have been annotated with the emotions they induce. We use these physiological signals to improve the performance of a lexicon-based sentiment classifier. We find that the combination of several biosignals can improve the ability of a text-based classifier to detect the presence of a sentiment in a text on a per-sentence level.
• 
  The German and International AI Network Data Set Stubbemann, Maximilian; Koopmann, Tobias (2020).
  • [ BibTeX ]
  • [ EndNote ]
  @article{koopmann-germanai_2020, author = {Stubbemann, Maximilian and Koopmann, Tobias}, keywords = {from:tobias.koopmann}, month = {mar}, publisher = {Zenodo}, title = {The German and International AI Network Data Set}, year = 2020 }

  %0 Journal Article %1 koopmann-germanai_2020 %A Stubbemann, Maximilian %A Koopmann, Tobias %D 2020 %I Zenodo %R 10.5281/zenodo.3693604 %T The German and International AI Network Data Set

• 
  On the Right Track! Analysing and Predicting Navigation Success in Wikipedia Koopmann, Tobias; Dallmann, Alexander; Hettinger, Lena; Niebler, Thomas; Hotho, Andreas in Proceedings of the 30th ACM Conference on Hypertext and Social Media, HT ’19 (2019). 143–152.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{Koopmann:2019:RTA:3342220.3343650, address = {New York, NY, USA}, author = {Koopmann, Tobias and Dallmann, Alexander and Hettinger, Lena and Niebler, Thomas and Hotho, Andreas}, booktitle = {Proceedings of the 30th ACM Conference on Hypertext and Social Media}, keywords = {from:schwemmlein}, pages = {143–152}, publisher = {ACM}, series = {HT '19}, title = {On the Right Track! Analysing and Predicting Navigation Success in Wikipedia}, year = 2019 }

  %0 Conference Paper %1 Koopmann:2019:RTA:3342220.3343650 %A Koopmann, Tobias %A Dallmann, Alexander %A Hettinger, Lena %A Niebler, Thomas %A Hotho, Andreas %B Proceedings of the 30th ACM Conference on Hypertext and Social Media %C New York, NY, USA %D 2019 %I ACM %P 143--152 %R 10.1145/3342220.3343650 %T On the Right Track! Analysing and Predicting Navigation Success in Wikipedia %U http://doi.acm.org/10.1145/3342220.3343650 %@ 978-1-4503-6885-8
• 
  Team Xenophilius Lovegood at SemEval-2019 Task 4: Hyperpartisanship Classification using Convolutional Neural Networks Zehe, Albin; Hettinger, Lena; Ernst, Stefan; Hauptmann, Christian; Hotho, Andreas in Proceedings of The 13th International Workshop on Semantic Evaluation (2019).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{zehe2019xenophilius, author = {Zehe, Albin and Hettinger, Lena and Ernst, Stefan and Hauptmann, Christian and Hotho, Andreas}, booktitle = {Proceedings of The 13th International Workshop on Semantic Evaluation}, keywords = {from:albinzehe}, publisher = {Association for Computational Linguistics}, title = {Team Xenophilius Lovegood at SemEval-2019 Task 4: Hyperpartisanship Classification using Convolutional Neural Networks}, year = 2019 }

  %0 Conference Paper %1 zehe2019xenophilius %A Zehe, Albin %A Hettinger, Lena %A Ernst, Stefan %A Hauptmann, Christian %A Hotho, Andreas %B Proceedings of The 13th International Workshop on Semantic Evaluation %D 2019 %I Association for Computational Linguistics %T Team Xenophilius Lovegood at SemEval-2019 Task 4: Hyperpartisanship Classification using Convolutional Neural Networks
• 
  Flow-based network traffic generation using Generative Adversarial Networks Ring, Markus; Schlör, Daniel; Landes, Dieter; Hotho, Andreas in Computers & Security (2019). 82 156–172.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Flow-based data sets are necessary for evaluating network-based intrusion detection systems (NIDS). In this work, we propose a novel methodology for generating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major challenge lies in the fact that GANs can only process continuous attributes. However, flow-based data inevitably contain categorical attributes such as IP addresses or port numbers. Therefore, we propose three different preprocessing approaches for flow-based data in order to transform them into continuous values. Further, we present a new method for evaluating the generated flow-based network traffic which uses domain knowledge to define quality tests. We use the three approaches for generating flow-based network traffic based on the CIDDS-001 data set. Experiments indicate that two of the three approaches are able to generate high quality data.

  @article{RING2019156, abstract = {Flow-based data sets are necessary for evaluating network-based intrusion detection systems (NIDS). In this work, we propose a novel methodology for generating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major challenge lies in the fact that GANs can only process continuous attributes. However, flow-based data inevitably contain categorical attributes such as IP addresses or port numbers. Therefore, we propose three different preprocessing approaches for flow-based data in order to transform them into continuous values. Further, we present a new method for evaluating the generated flow-based network traffic which uses domain knowledge to define quality tests. We use the three approaches for generating flow-based network traffic based on the CIDDS-001 data set. Experiments indicate that two of the three approaches are able to generate high quality data.}, author = {Ring, Markus and Schlör, Daniel and Landes, Dieter and Hotho, Andreas}, journal = {Computers & Security}, keywords = {traffic}, pages = {156 - 172}, title = {Flow-based network traffic generation using Generative Adversarial Networks}, volume = 82, year = 2019 }

  %0 Journal Article %1 RING2019156 %A Ring, Markus %A Schlör, Daniel %A Landes, Dieter %A Hotho, Andreas %D 2019 %J Computers & Security %P 156 - 172 %R https://doi.org/10.1016/j.cose.2018.12.012 %T Flow-based network traffic generation using Generative Adversarial Networks %U http://www.sciencedirect.com/science/article/pii/S0167404818308393 %V 82 %X Flow-based data sets are necessary for evaluating network-based intrusion detection systems (NIDS). In this work, we propose a novel methodology for generating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major challenge lies in the fact that GANs can only process continuous attributes. However, flow-based data inevitably contain categorical attributes such as IP addresses or port numbers. Therefore, we propose three different preprocessing approaches for flow-based data in order to transform them into continuous values. Further, we present a new method for evaluating the generated flow-based network traffic which uses domain knowledge to define quality tests. We use the three approaches for generating flow-based network traffic based on the CIDDS-001 data set. Experiments indicate that two of the three approaches are able to generate high quality data.
• 
  Detection of Scenes in Fiction Gius, Evelyn; Jannidis, Fotis; Krug, Markus; Zehe, Albin; Hotho, Andreas; Puppe, Frank; Krebs, Jonathan; Reiter, Nils; Wiedmer, Nathalie; Konle, Leonard in Proceedings of Digital Humanities 2019 (2019).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{gius2019detection, author = {Gius, Evelyn and Jannidis, Fotis and Krug, Markus and Zehe, Albin and Hotho, Andreas and Puppe, Frank and Krebs, Jonathan and Reiter, Nils and Wiedmer, Nathalie and Konle, Leonard}, booktitle = {Proceedings of Digital Humanities 2019}, keywords = {from:albinzehe}, title = {Detection of Scenes in Fiction}, year = 2019 }

  %0 Conference Paper %1 gius2019detection %A Gius, Evelyn %A Jannidis, Fotis %A Krug, Markus %A Zehe, Albin %A Hotho, Andreas %A Puppe, Frank %A Krebs, Jonathan %A Reiter, Nils %A Wiedmer, Nathalie %A Konle, Leonard %B Proceedings of Digital Humanities 2019 %D 2019 %T Detection of Scenes in Fiction
• 
  EClaiRE: Context Matters! – Comparing Word Embeddings for Relation Classification Hettinger, Lena; Zehe, Albin; Dallmann, Alexander; Hotho, Andreas in INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft, K. David, K. Geihs, M. Lange, G. Stumme (eds.) (2019). 191–204.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{mci/Hettinger2019, address = {Bonn}, author = {Hettinger, Lena and Zehe, Albin and Dallmann, Alexander and Hotho, Andreas}, booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft}, editor = {David, Klaus and Geihs, Kurt and Lange, Martin and Stumme, Gerd}, keywords = {from:schwemmlein}, pages = {191-204}, publisher = {Gesellschaft für Informatik e.V.}, title = {EClaiRE: Context Matters! – Comparing Word Embeddings for Relation Classification}, year = 2019 }

  %0 Conference Paper %1 mci/Hettinger2019 %A Hettinger, Lena %A Zehe, Albin %A Dallmann, Alexander %A Hotho, Andreas %B INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft %C Bonn %D 2019 %E David, Klaus %E Geihs, Kurt %E Lange, Martin %E Stumme, Gerd %I Gesellschaft für Informatik e.V. %P 191-204 %T EClaiRE: Context Matters! – Comparing Word Embeddings for Relation Classification
• 
  A survey of network-based intrusion detection data sets Ring, Markus; Wunderlich, Sarah; Scheuring, Deniz; Landes, Dieter; Hotho, Andreas in Comput. Secur. (2019). 86 147–167.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @article{ring2019survey, author = {Ring, Markus and Wunderlich, Sarah and Scheuring, Deniz and Landes, Dieter and Hotho, Andreas}, journal = {Comput. Secur.}, keywords = {survey}, pages = {147-167}, title = {A survey of network-based intrusion detection data sets}, volume = 86, year = 2019 }

  %0 Journal Article %1 ring2019survey %A Ring, Markus %A Wunderlich, Sarah %A Scheuring, Deniz %A Landes, Dieter %A Hotho, Andreas %D 2019 %J Comput. Secur. %P 147-167 %T A survey of network-based intrusion detection data sets %U http://dblp.uni-trier.de/db/journals/compsec/compsec86.html#RingWSLH19 %V 86
• 
  Solving Mathematical Exercises: Prediction of Students’ Success Wankerl, Sebastian; Götz, Gerhard; Hotho, Andreas in LWDA, CEUR Workshop Proceedings, R. Jäschke, M. Weidlich (eds.) (2019). (Vol. 2454) 190–194.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{wankerl2019solving, author = {Wankerl, Sebastian and Götz, Gerhard and Hotho, Andreas}, booktitle = {LWDA}, editor = {Jäschke, Robert and Weidlich, Matthias}, keywords = {from:hotho}, pages = {190-194}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {Solving Mathematical Exercises: Prediction of Students’ Success}, volume = 2454, year = 2019 }

  %0 Conference Paper %1 wankerl2019solving %A Wankerl, Sebastian %A Götz, Gerhard %A Hotho, Andreas %B LWDA %D 2019 %E Jäschke, Robert %E Weidlich, Matthias %I CEUR-WS.org %P 190-194 %T Solving Mathematical Exercises: Prediction of Students’ Success %U http://ceur-ws.org/Vol-2454/paper_84.pdf %V 2454
• 
  Comparison of System Call Representations for Intrusion Detection Wunderlich, Sarah; Ring, Markus; Landes, Dieter; Hotho, Andreas (2019).
  • [ BibTeX ]
  • [ EndNote ]
  @article{wunderlich2019comparison, author = {Wunderlich, Sarah and Ring, Markus and Landes, Dieter and Hotho, Andreas}, keywords = {system}, title = {Comparison of System Call Representations for Intrusion Detection}, year = 2019 }

  %0 Journal Article %1 wunderlich2019comparison %A Wunderlich, Sarah %A Ring, Markus %A Landes, Dieter %A Hotho, Andreas %D 2019 %T Comparison of System Call Representations for Intrusion Detection

• 
  Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data Kibanov, Mark; Becker, Martin; Müller, Juergen; Atzmüller, Martin; Hotho, Andreas; Stumme, Gerd in Proceedings of the 33rd Annual ACM Symposium on Applied Computing, SAC ’18 (2018). 857–865.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.

  @inproceedings{kibanov2018adaptive, abstract = {The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.}, address = {New York, NY, USA}, author = {Kibanov, Mark and Becker, Martin and Müller, Juergen and Atzmüller, Martin and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the 33rd Annual ACM Symposium on Applied Computing}, keywords = {spatial}, pages = {857–865}, publisher = {ACM}, series = {SAC '18}, title = {Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data}, year = 2018 }

  %0 Conference Paper %1 kibanov2018adaptive %A Kibanov, Mark %A Becker, Martin %A Müller, Juergen %A Atzmüller, Martin %A Hotho, Andreas %A Stumme, Gerd %B Proceedings of the 33rd Annual ACM Symposium on Applied Computing %C New York, NY, USA %D 2018 %I ACM %P 857--865 %R 10.1145/3167132.3167226 %T Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data %U http://doi.acm.org/10.1145/3167132.3167226 %X The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy. %@ 978-1-4503-5191-1
• 
  ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings Hettinger, Lena; Dallmann, Alexander; Zehe, Albin; Niebler, Thomas; Hotho, Andreas in Proceedings of International Workshop on Semantic Evaluation (SemEval-2018) (2018).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{hettinger2018semeval, address = {New Orleans, LA, USA}, author = {Hettinger, Lena and Dallmann, Alexander and Zehe, Albin and Niebler, Thomas and Hotho, Andreas}, booktitle = {Proceedings of International Workshop on Semantic Evaluation (SemEval-2018)}, keywords = {word}, title = {ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings}, year = 2018 }

  %0 Conference Paper %1 hettinger2018semeval %A Hettinger, Lena %A Dallmann, Alexander %A Zehe, Albin %A Niebler, Thomas %A Hotho, Andreas %B Proceedings of International Workshop on Semantic Evaluation (SemEval-2018) %C New Orleans, LA, USA %D 2018 %T ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings
• 
  Analysing Direct Speech in German Novels Jannidis, Fotis; Konle, Leonard; Zehe, Albin; Hotho, Andreas; Krug, Markus in DHd 2018 (2018).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{jannidis2018analysing, author = {Jannidis, Fotis and Konle, Leonard and Zehe, Albin and Hotho, Andreas and Krug, Markus}, booktitle = {DHd 2018}, keywords = {myown}, title = {Analysing Direct Speech in German Novels}, year = 2018 }

  %0 Conference Paper %1 jannidis2018analysing %A Jannidis, Fotis %A Konle, Leonard %A Zehe, Albin %A Hotho, Andreas %A Krug, Markus %B DHd 2018 %D 2018 %T Analysing Direct Speech in German Novels
• 
  ClaiRE at SemEval-2018 Task 7 - Extended Version Hettinger, Lena; Dallmann, Alexander; Zehe, Albin; Niebler, Thomas; Hotho, Andreas (2018).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  In this paper we describe our post-evaluation results for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1.1) and noisy data (subtask 1.2). Due to space limitations we publish an extended version of Hettinger et al. (2018) including further technical details and changes made to the preprocessing step in the post-evaluation phase. Due to these changes Classification of Relations using Embeddings (ClaiRE) achieved an improved F1 score of 75.11% for the first subtask and 81.44% for the second.

  @misc{hettinger2018claire, abstract = {In this paper we describe our post-evaluation results for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1.1) and noisy data (subtask 1.2). Due to space limitations we publish an extended version of Hettinger et al. (2018) including further technical details and changes made to the preprocessing step in the post-evaluation phase. Due to these changes Classification of Relations using Embeddings (ClaiRE) achieved an improved F1 score of 75.11% for the first subtask and 81.44% for the second.}, author = {Hettinger, Lena and Dallmann, Alexander and Zehe, Albin and Niebler, Thomas and Hotho, Andreas}, keywords = {tagging}, note = {cite arxiv:1804.05825Comment: This is the extended version for our work: ClaiRE at SemEval-2018 Task 7}, title = {ClaiRE at SemEval-2018 Task 7 - Extended Version}, year = 2018 }

  %0 Generic %1 hettinger2018claire %A Hettinger, Lena %A Dallmann, Alexander %A Zehe, Albin %A Niebler, Thomas %A Hotho, Andreas %D 2018 %T ClaiRE at SemEval-2018 Task 7 - Extended Version %U http://arxiv.org/abs/1804.05825 %X In this paper we describe our post-evaluation results for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1.1) and noisy data (subtask 1.2). Due to space limitations we publish an extended version of Hettinger et al. (2018) including further technical details and changes made to the preprocessing step in the post-evaluation phase. Due to these changes Classification of Relations using Embeddings (ClaiRE) achieved an improved F1 score of 75.11% for the first subtask and 81.44% for the second.
• 
  A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels Zehe, Albin; Schlör, Daniel; Henny-Krahmer, Ulrike; Becker, Martin; Hotho, Andreas in DH (2018).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{zehe2018whitebox, author = {Zehe, Albin and Schlör, Daniel and Henny-Krahmer, Ulrike and Becker, Martin and Hotho, Andreas}, booktitle = {DH}, keywords = {svn}, organization = {ADHO}, title = {A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels}, year = 2018 }

  %0 Conference Paper %1 zehe2018whitebox %A Zehe, Albin %A Schlör, Daniel %A Henny-Krahmer, Ulrike %A Becker, Martin %A Hotho, Andreas %B DH %D 2018 %T A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels
• 
  Healing Time Correlates With the Quality of Scaring: Results From a Prospective Randomized Control Donor Site Trial Werdin, Frank; Tenenhaus, Mayer; Becker, Martin; Rennekampff, Hans-Oliver in Dermatologic Surgery (2018). 44(4) 521–527.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{werdin2018healing, author = {Werdin, Frank and Tenenhaus, Mayer and Becker, Martin and Rennekampff, Hans-Oliver}, journal = {Dermatologic Surgery}, keywords = {from:becker}, number = 4, pages = {521–527}, publisher = {LWW}, title = {Healing Time Correlates With the Quality of Scaring: Results From a Prospective Randomized Control Donor Site Trial}, volume = 44, year = 2018 }

  %0 Journal Article %1 werdin2018healing %A Werdin, Frank %A Tenenhaus, Mayer %A Becker, Martin %A Rennekampff, Hans-Oliver %D 2018 %I LWW %J Dermatologic Surgery %N 4 %P 521--527 %T Healing Time Correlates With the Quality of Scaring: Results From a Prospective Randomized Control Donor Site Trial %V 44
• 
  Big-Data Helps SDN to Improve Application Specific Quality of Service Schwarzmann, Susanna; Blenk, Andreas; Dobrijevic, Ognjen; Jarschel, Michael; Hotho, Andreas; Zinner, Thomas; Wamser, Florian in Big Data and Software Defined Networks (2018).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  This chapter first provides an outline of the current results in the domains of: (a) quality-of-service (QoS) / quality-of-experience (QoE) control and management (CaM) for real-time multimedia services that is supported by software-defined networking (SDN), and (b) big data analytics and methods that are used for QoS/QoE CaM. Then, three specific use case scenarios with respect to video streaming services are presented, so as to illustrate the expected benefits of incorporating big data analytics into SDN-based CaM for the purposes of improving or optimizing QoS/QoE. In the end, we describe our vision and a high-level view of an SDN-based architecture for QoS/QoE CaM that is enriched with big data analytics' functional blocks and summarize corresponding challenges.

  @incollection{schwarzmann2018bigdata, abstract = {This chapter first provides an outline of the current results in the domains of: (a) quality-of-service (QoS) / quality-of-experience (QoE) control and management (CaM) for real-time multimedia services that is supported by software-defined networking (SDN), and (b) big data analytics and methods that are used for QoS/QoE CaM. Then, three specific use case scenarios with respect to video streaming services are presented, so as to illustrate the expected benefits of incorporating big data analytics into SDN-based CaM for the purposes of improving or optimizing QoS/QoE. In the end, we describe our vision and a high-level view of an SDN-based architecture for QoS/QoE CaM that is enriched with big data analytics' functional blocks and summarize corresponding challenges.}, author = {Schwarzmann, Susanna and Blenk, Andreas and Dobrijevic, Ognjen and Jarschel, Michael and Hotho, Andreas and Zinner, Thomas and Wamser, Florian}, booktitle = {Big Data and Software Defined Networks}, keywords = {service}, publisher = {IET}, title = {Big-Data Helps SDN to Improve Application Specific Quality of Service}, year = 2018 }

  %0 Book Section %1 schwarzmann2018bigdata %A Schwarzmann, Susanna %A Blenk, Andreas %A Dobrijevic, Ognjen %A Jarschel, Michael %A Hotho, Andreas %A Zinner, Thomas %A Wamser, Florian %B Big Data and Software Defined Networks %D 2018 %I IET %T Big-Data Helps SDN to Improve Application Specific Quality of Service %X This chapter first provides an outline of the current results in the domains of: (a) quality-of-service (QoS) / quality-of-experience (QoE) control and management (CaM) for real-time multimedia services that is supported by software-defined networking (SDN), and (b) big data analytics and methods that are used for QoS/QoE CaM. Then, three specific use case scenarios with respect to video streaming services are presented, so as to illustrate the expected benefits of incorporating big data analytics into SDN-based CaM for the purposes of improving or optimizing QoS/QoE. In the end, we describe our vision and a high-level view of an SDN-based architecture for QoS/QoE CaM that is enriched with big data analytics' functional blocks and summarize corresponding challenges.
• 
  Accessing Information with Tags: Search and Ranking Navarro Bullock, Beate; Hotho, Andreas; Stumme, Gerd in Social Information Access: Systems and Technologies, P. Brusilovsky, D. He (eds.) (2018). 310–343.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  With the growth of the Social Web, a variety of new web-based services arose and changed the way users interact with the internet and consume information. One central phenomenon was and is tagging which allows to manage, organize and access information in social systems. Tagging helps to manage all kinds of resources, making their access much easier. The first type of social tagging systems were social bookmarking systems, i.e., platforms for storing and sharing bookmarks on the web rather than just in the browser. Meanwhile, (hash-)tagging is central in many other Social Media systems such as social networking sites and micro-blogging platforms. To allow for efficient information access, special algorithms have been developed to guide the user, to search for information and to rank the content based on tagging information contributed by the users.

  @inbook{navarrobullock2018accessing, abstract = {With the growth of the Social Web, a variety of new web-based services arose and changed the way users interact with the internet and consume information. One central phenomenon was and is tagging which allows to manage, organize and access information in social systems. Tagging helps to manage all kinds of resources, making their access much easier. The first type of social tagging systems were social bookmarking systems, i.e., platforms for storing and sharing bookmarks on the web rather than just in the browser. Meanwhile, (hash-)tagging is central in many other Social Media systems such as social networking sites and micro-blogging platforms. To allow for efficient information access, special algorithms have been developed to guide the user, to search for information and to rank the content based on tagging information contributed by the users.}, address = {Cham}, author = {Navarro Bullock, Beate and Hotho, Andreas and Stumme, Gerd}, booktitle = {Social Information Access: Systems and Technologies}, editor = {Brusilovsky, Peter and He, Daqing}, keywords = {tag}, pages = {310–343}, publisher = {Springer International Publishing}, title = {Accessing Information with Tags: Search and Ranking}, year = 2018 }

  %0 Book Section %1 navarrobullock2018accessing %A Navarro Bullock, Beate %A Hotho, Andreas %A Stumme, Gerd %B Social Information Access: Systems and Technologies %C Cham %D 2018 %E Brusilovsky, Peter %E He, Daqing %I Springer International Publishing %P 310--343 %R 10.1007/978-3-319-90092-6_9 %T Accessing Information with Tags: Search and Ranking %U https://doi.org/10.1007/978-3-319-90092-6_9 %X With the growth of the Social Web, a variety of new web-based services arose and changed the way users interact with the internet and consume information. One central phenomenon was and is tagging which allows to manage, organize and access information in social systems. Tagging helps to manage all kinds of resources, making their access much easier. The first type of social tagging systems were social bookmarking systems, i.e., platforms for storing and sharing bookmarks on the web rather than just in the browser. Meanwhile, (hash-)tagging is central in many other Social Media systems such as social networking sites and micro-blogging platforms. To allow for efficient information access, special algorithms have been developed to guide the user, to search for information and to rank the content based on tagging information contributed by the users. %@ 978-3-319-90092-6
• 
  Burrows Zeta: Varianten und Evaluation Schöch, Christof; Calvo, José; Zehe, Albin; Hotho, Andreas in DHd 2018 (2018).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{schoch2018burrows, author = {Schöch, Christof and Calvo, José and Zehe, Albin and Hotho, Andreas}, booktitle = {DHd 2018}, keywords = {zeta}, title = {Burrows Zeta: Varianten und Evaluation}, year = 2018 }

  %0 Conference Paper %1 schoch2018burrows %A Schöch, Christof %A Calvo, José %A Zehe, Albin %A Hotho, Andreas %B DHd 2018 %D 2018 %T Burrows Zeta: Varianten und Evaluation
• 
  Burrows’ Zeta: Exploring and Evaluating Variants and Parameters Schöch, Christof; Schlör, Daniel; Zehe, Albin; Gebhard, Henning; Becker, Martin; Hotho, Andreas in DH (2018). 274–277.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  @inproceedings{schoech2018zeta, author = {Schöch, Christof and Schlör, Daniel and Zehe, Albin and Gebhard, Henning and Becker, Martin and Hotho, Andreas}, booktitle = {DH}, keywords = {zeta}, pages = {274-277}, title = {Burrows’ Zeta: Exploring and Evaluating Variants and Parameters}, year = 2018 }

  %0 Conference Paper %1 schoech2018zeta %A Schöch, Christof %A Schlör, Daniel %A Zehe, Albin %A Gebhard, Henning %A Becker, Martin %A Hotho, Andreas %B DH %D 2018 %P 274-277 %T Burrows’ Zeta: Exploring and Evaluating Variants and Parameters %U http://dblp.uni-trier.de/db/conf/dihu/dh2018.html#SchochSZG0H18
• 
  Air Trails -- Urban Air Quality Campaign Exploration Patterns Becker, Martin; Lautenschlager, Florian; Hotho, Andreas (2018).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{becker2018air, author = {Becker, Martin and Lautenschlager, Florian and Hotho, Andreas}, keywords = {project:p2map}, title = {Air Trails – Urban Air Quality Campaign Exploration Patterns}, year = 2018 }

  %0 Journal Article %1 becker2018air %A Becker, Martin %A Lautenschlager, Florian %A Hotho, Andreas %D 2018 %T Air Trails -- Urban Air Quality Campaign Exploration Patterns
• 
  pysubgroup: Easy-to-Use Subgroup Discovery in Python. Lemmerich, Florian; Becker, Martin in ECML/PKDD (3), Lecture Notes in Computer Science, U. Brefeld, E. Curry, E. Daly, B. MacNamee, A. Marascu, F. Pinelli, M. Berlingerio, N. Hurley (eds.) (2018). (Vol. 11053) 658–662.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{lemmerich2018pysubgroup, author = {Lemmerich, Florian and Becker, Martin}, booktitle = {ECML/PKDD (3)}, crossref = {conf/pkdd/2018-3}, editor = {Brefeld, Ulf and Curry, Edward and Daly, Elizabeth and MacNamee, Brian and Marascu, Alice and Pinelli, Fabio and Berlingerio, Michele and Hurley, Neil}, keywords = {from:becker}, pages = {658-662}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {pysubgroup: Easy-to-Use Subgroup Discovery in Python.}, volume = 11053, year = 2018 }

  %0 Conference Paper %1 lemmerich2018pysubgroup %A Lemmerich, Florian %A Becker, Martin %B ECML/PKDD (3) %D 2018 %E Brefeld, Ulf %E Curry, Edward %E Daly, Elizabeth %E MacNamee, Brian %E Marascu, Alice %E Pinelli, Fabio %E Berlingerio, Michele %E Hurley, Neil %I Springer %P 658-662 %T pysubgroup: Easy-to-Use Subgroup Discovery in Python. %U http://dblp.uni-trier.de/db/conf/pkdd/pkdd2018-3.html#Lemmerich018 %V 11053 %@ 978-3-030-10997-4
• 
  Flow-based Network Traffic Generation using Generative Adversarial Networks. Ring, Markus; Schlör, Daniel; Landes, Dieter; Hotho, Andreas in CoRR (2018). abs/1810.07795
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  Flow-based data sets are necessary for evaluating network-based intrusion de- tection systems (NIDS). In this work, we propose a novel methodology for gener- ating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major challenge lies in the fact that GANs can only process continuous at- tributes. However, flow-based data inevitably contain categorical attributes such as IP addresses or port numbers. Therefore, we propose three different preprocessing approaches for flow-based data in order to transform them into continuous values. Further, we present a new method for evaluating the gener- ated flow-based network traffic which uses domain knowledge to define quality tests. We use the three approaches for generating flow-based network traffic based on the CIDDS-001 data set. Experiments indicate that two of the three approaches are able to generate high quality data.

  @article{ring2018flowbased, abstract = {Flow-based data sets are necessary for evaluating network-based intrusion de- tection systems (NIDS). In this work, we propose a novel methodology for gener- ating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major challenge lies in the fact that GANs can only process continuous at- tributes. However, flow-based data inevitably contain categorical attributes such as IP addresses or port numbers. Therefore, we propose three different preprocessing approaches for flow-based data in order to transform them into continuous values. Further, we present a new method for evaluating the gener- ated flow-based network traffic which uses domain knowledge to define quality tests. We use the three approaches for generating flow-based network traffic based on the CIDDS-001 data set. Experiments indicate that two of the three approaches are able to generate high quality data.}, author = {Ring, Markus and Schlör, Daniel and Landes, Dieter and Hotho, Andreas}, journal = {CoRR}, keywords = {myown}, title = {Flow-based Network Traffic Generation using Generative Adversarial Networks.}, volume = {abs/1810.07795}, year = 2018 }

  %0 Journal Article %1 ring2018flowbased %A Ring, Markus %A Schlör, Daniel %A Landes, Dieter %A Hotho, Andreas %D 2018 %J CoRR %T Flow-based Network Traffic Generation using Generative Adversarial Networks. %U http://dblp.uni-trier.de/db/journals/corr/corr1810.html#abs-1810-07795 %V abs/1810.07795 %X Flow-based data sets are necessary for evaluating network-based intrusion de- tection systems (NIDS). In this work, we propose a novel methodology for gener- ating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major challenge lies in the fact that GANs can only process continuous at- tributes. However, flow-based data inevitably contain categorical attributes such as IP addresses or port numbers. Therefore, we propose three different preprocessing approaches for flow-based data in order to transform them into continuous values. Further, we present a new method for evaluating the gener- ated flow-based network traffic which uses domain knowledge to define quality tests. We use the three approaches for generating flow-based network traffic based on the CIDDS-001 data set. Experiments indicate that two of the three approaches are able to generate high quality data.
• 
  Detection of slow port scans in flow-based network traffic Ring, Markus; Landes, Dieter; Hotho, Andreas in PLOS ONE (2018). 13(9) 1–18.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  Frequently, port scans are early indicators of more serious attacks. Unfortunately, the detection of slow port scans in company networks is challenging due to the massive amount of network data. This paper proposes an innovative approach for preprocessing flow-based data which is specifically tailored to the detection of slow port scans. The preprocessing chain generates new objects based on flow-based data aggregated over time windows while taking domain knowledge as well as additional knowledge about the network structure into account. The computed objects are used as input for the further analysis. Based on these objects, we propose two different approaches for detection of slow port scans. One approach is unsupervised and uses sequential hypothesis testing whereas the other approach is supervised and uses classification algorithms. We compare both approaches with existing port scan detection algorithms on the flow-based CIDDS-001 data set. Experiments indicate that the proposed approaches achieve better detection rates and exhibit less false alarms than similar algorithms.

  @article{10.1371/journal.pone.0204507, abstract = {Frequently, port scans are early indicators of more serious attacks. Unfortunately, the detection of slow port scans in company networks is challenging due to the massive amount of network data. This paper proposes an innovative approach for preprocessing flow-based data which is specifically tailored to the detection of slow port scans. The preprocessing chain generates new objects based on flow-based data aggregated over time windows while taking domain knowledge as well as additional knowledge about the network structure into account. The computed objects are used as input for the further analysis. Based on these objects, we propose two different approaches for detection of slow port scans. One approach is unsupervised and uses sequential hypothesis testing whereas the other approach is supervised and uses classification algorithms. We compare both approaches with existing port scan detection algorithms on the flow-based CIDDS-001 data set. Experiments indicate that the proposed approaches achieve better detection rates and exhibit less false alarms than similar algorithms.}, author = {Ring, Markus and Landes, Dieter and Hotho, Andreas}, journal = {PLOS ONE}, keywords = {myown}, month = {09}, number = 9, pages = {1-18}, publisher = {Public Library of Science}, title = {Detection of slow port scans in flow-based network traffic}, volume = 13, year = 2018 }

  %0 Journal Article %1 10.1371/journal.pone.0204507 %A Ring, Markus %A Landes, Dieter %A Hotho, Andreas %D 2018 %I Public Library of Science %J PLOS ONE %N 9 %P 1-18 %R 10.1371/journal.pone.0204507 %T Detection of slow port scans in flow-based network traffic %U https://doi.org/10.1371/journal.pone.0204507 %V 13 %X Frequently, port scans are early indicators of more serious attacks. Unfortunately, the detection of slow port scans in company networks is challenging due to the massive amount of network data. This paper proposes an innovative approach for preprocessing flow-based data which is specifically tailored to the detection of slow port scans. The preprocessing chain generates new objects based on flow-based data aggregated over time windows while taking domain knowledge as well as additional knowledge about the network structure into account. The computed objects are used as input for the further analysis. Based on these objects, we propose two different approaches for detection of slow port scans. One approach is unsupervised and uses sequential hypothesis testing whereas the other approach is supervised and uses classification algorithms. We compare both approaches with existing port scan detection algorithms on the flow-based CIDDS-001 data set. Experiments indicate that the proposed approaches achieve better detection rates and exhibit less false alarms than similar algorithms.
• 
  EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data Lautenschlager, Florian; Becker, Martin; Steininger, Michael; Hotho, Andreas in Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018, D. Burghardt, S. Chen, G. Andrienko, N. Andrienko, R. Purves, A. Diehl (eds.) (2018).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{lautenschlager2018everyaware, author = {Lautenschlager, Florian and Becker, Martin and Steininger, Michael and Hotho, Andreas}, booktitle = {Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018}, editor = {Burghardt, Dirk and Chen, Siming and Andrienko, Gennady and Andrienko, Nathalia and Purves, Ross and Diehl, Alexandra}, keywords = {project:p2map}, month = {oct}, publisher = {KOPS}, title = {EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data}, year = 2018 }

  %0 Conference Paper %1 lautenschlager2018everyaware %A Lautenschlager, Florian %A Becker, Martin %A Steininger, Michael %A Hotho, Andreas %B Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018 %D 2018 %E Burghardt, Dirk %E Chen, Siming %E Andrienko, Gennady %E Andrienko, Nathalia %E Purves, Ross %E Diehl, Alexandra %I KOPS %T EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data

• 
  A Bayesian Method for Comparing Hypotheses About Human Trails Singer, Philipp; Helic, Denis; Hotho, Andreas; Strohmaier, Markus in ACM Trans. Web (2017). 11(3) 14:1–14:29.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  When users interact with the Web today, they leave sequential digital trails on a massive scale. Examples of such human trails include Web navigation, sequences of online restaurant reviews, or online music play lists. Understanding the factors that drive the production of these trails can be useful, for example, for improving underlying network structures, predicting user clicks, or enhancing recommendations. In this work, we present a method called HypTrails for comparing a set of hypotheses about human trails on the Web, where hypotheses represent beliefs about transitions between states. Our method utilizes Markov chain models with Bayesian inference. The main idea is to incorporate hypotheses as informative Dirichlet priors and to calculate the evidence of the data under them. For eliciting Dirichlet priors from hypotheses, we present an adaption of the so-called (trial) roulette method, and to compare the relative plausibility of hypotheses, we employ Bayes factors. We demonstrate the general mechanics and applicability of HypTrails by performing experiments with (i) synthetic trails for which we control the mechanisms that have produced them and (ii) empirical trails stemming from different domains including Web site navigation, business reviews, and online music played. Our work expands the repertoire of methods available for studying human trails.

  @article{singer2017bayesian, abstract = {When users interact with the Web today, they leave sequential digital trails on a massive scale. Examples of such human trails include Web navigation, sequences of online restaurant reviews, or online music play lists. Understanding the factors that drive the production of these trails can be useful, for example, for improving underlying network structures, predicting user clicks, or enhancing recommendations. In this work, we present a method called HypTrails for comparing a set of hypotheses about human trails on the Web, where hypotheses represent beliefs about transitions between states. Our method utilizes Markov chain models with Bayesian inference. The main idea is to incorporate hypotheses as informative Dirichlet priors and to calculate the evidence of the data under them. For eliciting Dirichlet priors from hypotheses, we present an adaption of the so-called (trial) roulette method, and to compare the relative plausibility of hypotheses, we employ Bayes factors. We demonstrate the general mechanics and applicability of HypTrails by performing experiments with (i) synthetic trails for which we control the mechanisms that have produced them and (ii) empirical trails stemming from different domains including Web site navigation, business reviews, and online music played. Our work expands the repertoire of methods available for studying human trails.}, address = {New York, NY, USA}, author = {Singer, Philipp and Helic, Denis and Hotho, Andreas and Strohmaier, Markus}, journal = {ACM Trans. Web}, keywords = {version}, month = {jun}, number = 3, pages = {14:1–14:29}, publisher = {ACM}, title = {A Bayesian Method for Comparing Hypotheses About Human Trails}, volume = 11, year = 2017 }

  %0 Journal Article %1 singer2017bayesian %A Singer, Philipp %A Helic, Denis %A Hotho, Andreas %A Strohmaier, Markus %C New York, NY, USA %D 2017 %I ACM %J ACM Trans. Web %N 3 %P 14:1--14:29 %R 10.1145/3054950 %T A Bayesian Method for Comparing Hypotheses About Human Trails %U http://doi.acm.org/10.1145/3054950 %V 11 %X When users interact with the Web today, they leave sequential digital trails on a massive scale. Examples of such human trails include Web navigation, sequences of online restaurant reviews, or online music play lists. Understanding the factors that drive the production of these trails can be useful, for example, for improving underlying network structures, predicting user clicks, or enhancing recommendations. In this work, we present a method called HypTrails for comparing a set of hypotheses about human trails on the Web, where hypotheses represent beliefs about transitions between states. Our method utilizes Markov chain models with Bayesian inference. The main idea is to incorporate hypotheses as informative Dirichlet priors and to calculate the evidence of the data under them. For eliciting Dirichlet priors from hypotheses, we present an adaption of the so-called (trial) roulette method, and to compare the relative plausibility of hypotheses, we employ Bayes factors. We demonstrate the general mechanics and applicability of HypTrails by performing experiments with (i) synthetic trails for which we control the mechanisms that have produced them and (ii) empirical trails stemming from different domains including Web site navigation, business reviews, and online music played. Our work expands the repertoire of methods available for studying human trails.
• 
  Participatory sensing, opinions and collective awareness Loreto, Vittorio; Haklay, Mordechai; Hotho, Andreas; Servedio, Vito C. P.; Stumme, Gerd; Theunis, Jan; Tria, Francesca (2017). Springer.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @book{loreto2017participatory, editor = {Loreto, Vittorio and Haklay, Mordechai and Hotho, Andreas and Servedio, Vito C. P. and Stumme, Gerd and Theunis, Jan and Tria, Francesca}, keywords = {sensing}, publisher = {Springer}, title = {Participatory sensing, opinions and collective awareness}, year = 2017 }

  %0 Book %1 loreto2017participatory %D 2017 %E Loreto, Vittorio %E Haklay, Mordechai %E Hotho, Andreas %E Servedio, Vito C. P. %E Stumme, Gerd %E Theunis, Jan %E Tria, Francesca %I Springer %T Participatory sensing, opinions and collective awareness %@ 9783319256580 3319256580
• 
  IP2Vec: Learning Similarities Between IP Addresses Ring, Markus; Landes, Dieter; Dallmann, Alexander; Hotho, Andreas in 2017 IEEE International Conference on Data Mining Workshops (ICDMW) (2017). 657–666.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @article{ring2017ip2vec, author = {Ring, Markus and Landes, Dieter and Dallmann, Alexander and Hotho, Andreas}, journal = {2017 IEEE International Conference on Data Mining Workshops (ICDMW)}, keywords = {similarity}, pages = {657-666}, title = {IP2Vec: Learning Similarities Between IP Addresses}, type = {Publication}, year = 2017 }

  %0 Journal Article %1 ring2017ip2vec %A Ring, Markus %A Landes, Dieter %A Dallmann, Alexander %A Hotho, Andreas %D 2017 %J 2017 IEEE International Conference on Data Mining Workshops (ICDMW) %P 657-666 %R 10.1109/ICDMW.2017.93 %T IP2Vec: Learning Similarities Between IP Addresses %@ 978-1-5386-3800-2
• 
  Flow-based benchmark data sets for intrusion detection Ring, Markus; Wunderlich, Sarah; Gr{\"u}dl, Dominik; Landes, Dieter; Hotho, Andreas in Proceedings of the 16th European Conference on Cyber Warfare and Security (2017). 361–369.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{ring2017flow, author = {Ring, Markus and Wunderlich, Sarah and Gr{\"u}dl, Dominik and Landes, Dieter and Hotho, Andreas}, booktitle = {Proceedings of the 16th European Conference on Cyber Warfare and Security}, keywords = {security}, pages = {361–369}, title = {Flow-based benchmark data sets for intrusion detection}, year = 2017 }

  %0 Conference Paper %1 ring2017flow %A Ring, Markus %A Wunderlich, Sarah %A Gr{\"u}dl, Dominik %A Landes, Dieter %A Hotho, Andreas %B Proceedings of the 16th European Conference on Cyber Warfare and Security %D 2017 %P 361--369 %T Flow-based benchmark data sets for intrusion detection
• 
  Comparing Hypotheses About Sequential Data: A Bayesian Approach and Its Applications Lemmerich, Florian; Singer, Philipp; Becker, Martin; Espin-Noboa, Lisette; Dimitrov, Dimitar; Helic, Denis; Hotho, Andreas; Strohmaier, Markus in Joint European Conference on Machine Learning and Knowledge Discovery in Databases (2017). 354–357.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{lemmerich2017comparing, author = {Lemmerich, Florian and Singer, Philipp and Becker, Martin and Espin-Noboa, Lisette and Dimitrov, Dimitar and Helic, Denis and Hotho, Andreas and Strohmaier, Markus}, booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases}, keywords = {from:becker}, organization = {Springer}, pages = {354–357}, title = {Comparing Hypotheses About Sequential Data: A Bayesian Approach and Its Applications}, year = 2017 }

  %0 Conference Paper %1 lemmerich2017comparing %A Lemmerich, Florian %A Singer, Philipp %A Becker, Martin %A Espin-Noboa, Lisette %A Dimitrov, Dimitar %A Helic, Denis %A Hotho, Andreas %A Strohmaier, Markus %B Joint European Conference on Machine Learning and Knowledge Discovery in Databases %D 2017 %P 354--357 %T Comparing Hypotheses About Sequential Data: A Bayesian Approach and Its Applications
• 
  Creation of Flow-Based Data Sets for Intrusion Detection Ring, Markus; Wunderlich, Sarah; Grüdl, Dominik; Landes, Dieter; Hotho, Andreas in Journal of Information Warfare (2017). 16(4) 41–54.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Publicly available labelled data sets are necessary for evaluating anomaly-based Intrusion Detection Systems (IDS). However, existing data sets are often not up-to-date or not yet published because of privacy concerns. This paper identifies requirements for good data sets and proposes an approach for their generation. The key idea is to use a test environment and emulate realistic user behaviour with parameterised scripts on the clients. Comprehensive logging mechanisms provide additional information which may be used for a better understanding of the inner dynamics of an IDS. Finally, the proposed approach is used to generate the flow-based CIDDS-002 data set.

  @article{ring2017creation, abstract = {Publicly available labelled data sets are necessary for evaluating anomaly-based Intrusion Detection Systems (IDS). However, existing data sets are often not up-to-date or not yet published because of privacy concerns. This paper identifies requirements for good data sets and proposes an approach for their generation. The key idea is to use a test environment and emulate realistic user behaviour with parameterised scripts on the clients. Comprehensive logging mechanisms provide additional information which may be used for a better understanding of the inner dynamics of an IDS. Finally, the proposed approach is used to generate the flow-based CIDDS-002 data set.}, author = {Ring, Markus and Wunderlich, Sarah and Grüdl, Dominik and Landes, Dieter and Hotho, Andreas}, journal = {Journal of Information Warfare}, keywords = {security:selected}, month = {Dez}, number = 4, pages = {41-54}, title = {Creation of Flow-Based Data Sets for Intrusion Detection}, volume = 16, year = 2017 }

  %0 Journal Article %1 ring2017creation %A Ring, Markus %A Wunderlich, Sarah %A Grüdl, Dominik %A Landes, Dieter %A Hotho, Andreas %D 2017 %J Journal of Information Warfare %N 4 %P 41-54 %T Creation of Flow-Based Data Sets for Intrusion Detection %U https://www.jinfowar.com/journal/volume-16-issue-4/creation-flow-based-data-sets-intrusion-detection %V 16 %X Publicly available labelled data sets are necessary for evaluating anomaly-based Intrusion Detection Systems (IDS). However, existing data sets are often not up-to-date or not yet published because of privacy concerns. This paper identifies requirements for good data sets and proposes an approach for their generation. The key idea is to use a test environment and emulate realistic user behaviour with parameterised scripts on the clients. Comprehensive logging mechanisms provide additional information which may be used for a better understanding of the inner dynamics of an IDS. Finally, the proposed approach is used to generate the flow-based CIDDS-002 data set.
• 
  Improving Session Recommendation with Recurrent Neural Networks by Exploiting Dwell Time. Dallmann, Alexander; Grimm, Alexander; Pölitz, Christian; Zoller, Daniel; Hotho, Andreas in CoRR (2017). abs/1706.10231
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{journals/corr/DallmannGPZH17, author = {Dallmann, Alexander and Grimm, Alexander and Pölitz, Christian and Zoller, Daniel and Hotho, Andreas}, journal = {CoRR}, keywords = {session}, title = {Improving Session Recommendation with Recurrent Neural Networks by Exploiting Dwell Time.}, volume = {abs/1706.10231}, year = 2017 }

  %0 Journal Article %1 journals/corr/DallmannGPZH17 %A Dallmann, Alexander %A Grimm, Alexander %A Pölitz, Christian %A Zoller, Daniel %A Hotho, Andreas %D 2017 %J CoRR %T Improving Session Recommendation with Recurrent Neural Networks by Exploiting Dwell Time. %U http://dblp.uni-trier.de/db/journals/corr/corr1706.html#DallmannGPZH17 %V abs/1706.10231
• 
  Neutralising the Authorial Signal in Delta by Penalization: Stylometric Clustering of Genre in Spanish Novels. Tello, José Calvo; Schlör, Daniel; Henny-Krahmer, Ulrike; Schöch, Christof in DH, R. Lewis, C. Raynor, D. Forest, M. Sinatra, S. Sinclair (eds.) (2017).
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{conf/dihu/TelloSHS17, author = {Tello, José Calvo and Schlör, Daniel and Henny-Krahmer, Ulrike and Schöch, Christof}, booktitle = {DH}, crossref = {conf/dihu/2017}, editor = {Lewis, Rhian and Raynor, Cecily and Forest, Dominic and Sinatra, Michael and Sinclair, Stéfan}, keywords = {from:daschloer}, publisher = {Alliance of Digital Humanities Organizations (ADHO)}, title = {Neutralising the Authorial Signal in Delta by Penalization: Stylometric Clustering of Genre in Spanish Novels.}, year = 2017 }

  %0 Conference Paper %1 conf/dihu/TelloSHS17 %A Tello, José Calvo %A Schlör, Daniel %A Henny-Krahmer, Ulrike %A Schöch, Christof %B DH %D 2017 %E Lewis, Rhian %E Raynor, Cecily %E Forest, Dominic %E Sinatra, Michael %E Sinclair, Stéfan %I Alliance of Digital Humanities Organizations (ADHO) %T Neutralising the Authorial Signal in Delta by Penalization: Stylometric Clustering of Genre in Spanish Novels. %U http://dblp.uni-trier.de/db/conf/dihu/dh2017.html#TelloSHS17
• 
  Towards Sentiment Analysis on German Literature Zehe, Albin; Becker, Martin; Jannidis, Fotis; Hotho, Andreas (2017).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{zehe2017sentiment, author = {Zehe, Albin and Becker, Martin and Jannidis, Fotis and Hotho, Andreas}, keywords = {sentimentanalysis}, title = {Towards Sentiment Analysis on German Literature}, year = 2017 }

  %0 Conference Paper %1 zehe2017sentiment %A Zehe, Albin %A Becker, Martin %A Jannidis, Fotis %A Hotho, Andreas %D 2017 %T Towards Sentiment Analysis on German Literature
• 
  Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning Niebler, Thomas; Becker, Martin; Pölitz, Christian; Hotho, Andreas in ISWC’17 (2017).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{niebler2017learning_3, author = {Niebler, Thomas and Becker, Martin and Pölitz, Christian and Hotho, Andreas}, booktitle = {ISWC'17}, keywords = {semantics}, title = {Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning}, year = 2017 }

  %0 Conference Paper %1 niebler2017learning_3 %A Niebler, Thomas %A Becker, Martin %A Pölitz, Christian %A Hotho, Andreas %B ISWC'17 %D 2017 %T Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning
• 
  Applications for Environmental Sensing in EveryAware Atzmueller, Martin; Becker, Martin; Molino, Andrea; Mueller, Juergen; Peters, Jan; S{\^\i}rbu, Alina in Participatory Sensing, Opinions and Collective Awareness (2017). 135–155.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @incollection{atzmueller2017applications, author = {Atzmueller, Martin and Becker, Martin and Molino, Andrea and Mueller, Juergen and Peters, Jan and S{\^\i}rbu, Alina}, booktitle = {Participatory Sensing, Opinions and Collective Awareness}, keywords = {sensing}, pages = {135–155}, publisher = {Springer}, title = {Applications for Environmental Sensing in EveryAware}, year = 2017 }

  %0 Book Section %1 atzmueller2017applications %A Atzmueller, Martin %A Becker, Martin %A Molino, Andrea %A Mueller, Juergen %A Peters, Jan %A S{\^\i}rbu, Alina %B Participatory Sensing, Opinions and Collective Awareness %D 2017 %I Springer %P 135--155 %T Applications for Environmental Sensing in EveryAware
• 
  Leveraging User-Interactions for Time-Aware Tag Recommendations Zoller, Daniel; Doerfel, Stephan; Pölitz, Christian; Hotho, Andreas in Proceedings of the Workshop on Temporal Reasoning in Recommender Systems, {CEUR} Workshop Proceedings (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  For the popular task of tag recommendation, various (complex) approaches have been proposed. Recently however, research has focused on heuristics with low computational effort and particularly, a time-aware heuristic, called BLL, has been shown to compare well to various state-of-the-art methods. Here, we follow up on these results by presenting another time-aware approach leveraging user interaction data in an easily interpretable, on-the-fly computable approach that can successfully be combined with BLL. We investigate the influence of time as a parameter in that approach, and we demonstrate the effectiveness of the proposed method using two datasets from the popular public social tagging system BibSonomy.

  @inproceedings{zoller2017leveraging, abstract = {For the popular task of tag recommendation, various (complex) approaches have been proposed. Recently however, research has focused on heuristics with low computational effort and particularly, a time-aware heuristic, called BLL, has been shown to compare well to various state-of-the-art methods. Here, we follow up on these results by presenting another time-aware approach leveraging user interaction data in an easily interpretable, on-the-fly computable approach that can successfully be combined with BLL. We investigate the influence of time as a parameter in that approach, and we demonstrate the effectiveness of the proposed method using two datasets from the popular public social tagging system BibSonomy.}, author = {Zoller, Daniel and Doerfel, Stephan and Pölitz, Christian and Hotho, Andreas}, booktitle = {Proceedings of the Workshop on Temporal Reasoning in Recommender Systems}, keywords = {user}, series = {{CEUR} Workshop Proceedings}, title = {Leveraging User-Interactions for Time-Aware Tag Recommendations}, year = 2017 }

  %0 Conference Paper %1 zoller2017leveraging %A Zoller, Daniel %A Doerfel, Stephan %A Pölitz, Christian %A Hotho, Andreas %B Proceedings of the Workshop on Temporal Reasoning in Recommender Systems %D 2017 %T Leveraging User-Interactions for Time-Aware Tag Recommendations %X For the popular task of tag recommendation, various (complex) approaches have been proposed. Recently however, research has focused on heuristics with low computational effort and particularly, a time-aware heuristic, called BLL, has been shown to compare well to various state-of-the-art methods. Here, we follow up on these results by presenting another time-aware approach leveraging user interaction data in an easily interpretable, on-the-fly computable approach that can successfully be combined with BLL. We investigate the influence of time as a parameter in that approach, and we demonstrate the effectiveness of the proposed method using two datasets from the popular public social tagging system BibSonomy.
• 
  Learning Semantic Relatedness From Human Feedback Using Metric Learning Niebler, Thomas; Becker, Martin; Pölitz, Christian; Hotho, Andreas (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated fashion, many relatedness measures have been proposed. However, most of these metrics only encode information contained in the underlying corpus and thus do not directly model human intuition. To solve this, we propose to utilize a metric learning approach to improve existing semantic relatedness measures by learning from additional information, such as explicit human feedback. For this, we argue to use word embeddings instead of traditional high-dimensional vector representations in order to leverage their semantic density and to reduce computational cost. We rigorously test our approach on several domains including tagging data as well as publicly available embeddings based on Wikipedia texts and navigation. Human feedback about semantic relatedness for learning and evaluation is extracted from publicly available datasets such as MEN or WS-353. We find that our method can significantly improve semantic relatedness measures by learning from additional information, such as explicit human feedback. For tagging data, we are the first to generate and study embeddings. Our results are of special interest for ontology and recommendation engineers, but also for any other researchers and practitioners of Semantic Web techniques.

  @misc{niebler2017learning, abstract = {Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated fashion, many relatedness measures have been proposed. However, most of these metrics only encode information contained in the underlying corpus and thus do not directly model human intuition. To solve this, we propose to utilize a metric learning approach to improve existing semantic relatedness measures by learning from additional information, such as explicit human feedback. For this, we argue to use word embeddings instead of traditional high-dimensional vector representations in order to leverage their semantic density and to reduce computational cost. We rigorously test our approach on several domains including tagging data as well as publicly available embeddings based on Wikipedia texts and navigation. Human feedback about semantic relatedness for learning and evaluation is extracted from publicly available datasets such as MEN or WS-353. We find that our method can significantly improve semantic relatedness measures by learning from additional information, such as explicit human feedback. For tagging data, we are the first to generate and study embeddings. Our results are of special interest for ontology and recommendation engineers, but also for any other researchers and practitioners of Semantic Web techniques.}, author = {Niebler, Thomas and Becker, Martin and Pölitz, Christian and Hotho, Andreas}, keywords = {from:thoni}, note = {cite arxiv:1705.07425}, title = {Learning Semantic Relatedness From Human Feedback Using Metric Learning}, year = 2017 }

  %0 Generic %1 niebler2017learning %A Niebler, Thomas %A Becker, Martin %A Pölitz, Christian %A Hotho, Andreas %D 2017 %T Learning Semantic Relatedness From Human Feedback Using Metric Learning %U http://arxiv.org/abs/1705.07425 %X Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated fashion, many relatedness measures have been proposed. However, most of these metrics only encode information contained in the underlying corpus and thus do not directly model human intuition. To solve this, we propose to utilize a metric learning approach to improve existing semantic relatedness measures by learning from additional information, such as explicit human feedback. For this, we argue to use word embeddings instead of traditional high-dimensional vector representations in order to leverage their semantic density and to reduce computational cost. We rigorously test our approach on several domains including tagging data as well as publicly available embeddings based on Wikipedia texts and navigation. Human feedback about semantic relatedness for learning and evaluation is extracted from publicly available datasets such as MEN or WS-353. We find that our method can significantly improve semantic relatedness measures by learning from additional information, such as explicit human feedback. For tagging data, we are the first to generate and study embeddings. Our results are of special interest for ontology and recommendation engineers, but also for any other researchers and practitioners of Semantic Web techniques.
• 
  Sedentary Behavior among National Elite Rowers during Off-Training—A Pilot Study Sperlich, Billy; Becker, Martin; Hotho, Andreas; Wallmann-Sperlich, Birgit; Sareban, Mahdi; Winkert, Kay; Steinacker, Jürgen M.; Treff, Gunnar in Frontiers in Physiology (2017). 8 655.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  The aim of this pilot study was to analyze the off-training physical activity (PA) profile in national elite German U23 rowers during 31 days of their preparation period. The hours spent in each PA category (i.e. sedentary: <1.5 MET; light physical activity: 1.5–3 MET; moderate physical activity: 3–6 MET and vigorous intense physical activity: >6 MET) were calculated for every valid day (i.e. > 480 min of wear time). The off-training PA during 21 weekdays and 10 weekend days of the final 11-wk preparation period was assessed by a wrist-worn multisensory device (Microsoft Band II (MSBII)). A total of 11 rowers provided valid data (i.e. > 480 min/day) for 11.6 week days and 4.8 weekend days during the 31 days observation period. The average sedentary time was 11.63±1.25 hours per day during the week and 12.49±1.10 hours per day on the weekend, with a tendency to be higher on the weekend compared to weekdays (p = 0.06; d = 0.73). The average time in light, moderate and vigorous PA during the weekdays was 1.27±1.15, 0.76±0.37, 0.51±0.44 hours per day and 0.67±0.43, 0.59±0.37, 0.53±0.32 hours per weekend day. Light physical activity was higher during weekdays compared to the weekend (p = 0.04; d = 0.69) Based on our pilot study of eleven national elite rowers we conclude that rowers display a considerable sedentary off-training behavior of more than 11.5 hours/day.

  @article{sperlich2017sedentary, abstract = {The aim of this pilot study was to analyze the off-training physical activity (PA) profile in national elite German U23 rowers during 31 days of their preparation period. The hours spent in each PA category (i.e. sedentary: <1.5 MET; light physical activity: 1.5–3 MET; moderate physical activity: 3–6 MET and vigorous intense physical activity: >6 MET) were calculated for every valid day (i.e. > 480 min of wear time). The off-training PA during 21 weekdays and 10 weekend days of the final 11-wk preparation period was assessed by a wrist-worn multisensory device (Microsoft Band II (MSBII)). A total of 11 rowers provided valid data (i.e. > 480 min/day) for 11.6 week days and 4.8 weekend days during the 31 days observation period. The average sedentary time was 11.63±1.25 hours per day during the week and 12.49±1.10 hours per day on the weekend, with a tendency to be higher on the weekend compared to weekdays (p = 0.06; d = 0.73). The average time in light, moderate and vigorous PA during the weekdays was 1.27±1.15, 0.76±0.37, 0.51±0.44 hours per day and 0.67±0.43, 0.59±0.37, 0.53±0.32 hours per weekend day. Light physical activity was higher during weekdays compared to the weekend (p = 0.04; d = 0.69) Based on our pilot study of eleven national elite rowers we conclude that rowers display a considerable sedentary off-training behavior of more than 11.5 hours/day.}, author = {Sperlich, Billy and Becker, Martin and Hotho, Andreas and Wallmann-Sperlich, Birgit and Sareban, Mahdi and Winkert, Kay and Steinacker, Jürgen M. and Treff, Gunnar}, journal = {Frontiers in Physiology}, keywords = {from:becker}, pages = 655, title = {Sedentary Behavior among National Elite Rowers during Off-Training—A Pilot Study}, volume = 8, year = 2017 }

  %0 Journal Article %1 sperlich2017sedentary %A Sperlich, Billy %A Becker, Martin %A Hotho, Andreas %A Wallmann-Sperlich, Birgit %A Sareban, Mahdi %A Winkert, Kay %A Steinacker, Jürgen M. %A Treff, Gunnar %D 2017 %J Frontiers in Physiology %P 655 %R 10.3389/fphys.2017.00655 %T Sedentary Behavior among National Elite Rowers during Off-Training—A Pilot Study %U http://journal.frontiersin.org/article/10.3389/fphys.2017.00655 %V 8 %X The aim of this pilot study was to analyze the off-training physical activity (PA) profile in national elite German U23 rowers during 31 days of their preparation period. The hours spent in each PA category (i.e. sedentary: <1.5 MET; light physical activity: 1.5–3 MET; moderate physical activity: 3–6 MET and vigorous intense physical activity: >6 MET) were calculated for every valid day (i.e. > 480 min of wear time). The off-training PA during 21 weekdays and 10 weekend days of the final 11-wk preparation period was assessed by a wrist-worn multisensory device (Microsoft Band II (MSBII)). A total of 11 rowers provided valid data (i.e. > 480 min/day) for 11.6 week days and 4.8 weekend days during the 31 days observation period. The average sedentary time was 11.63±1.25 hours per day during the week and 12.49±1.10 hours per day on the weekend, with a tendency to be higher on the weekend compared to weekdays (p = 0.06; d = 0.73). The average time in light, moderate and vigorous PA during the weekdays was 1.27±1.15, 0.76±0.37, 0.51±0.44 hours per day and 0.67±0.43, 0.59±0.37, 0.53±0.32 hours per weekend day. Light physical activity was higher during weekdays compared to the weekend (p = 0.04; d = 0.69) Based on our pilot study of eleven national elite rowers we conclude that rowers display a considerable sedentary off-training behavior of more than 11.5 hours/day.
• 
  Collective Sensing Platforms Atzmueller, Martin; Becker, Martin; Mueller, Juergen in Participatory Sensing, Opinions and Collective Awareness (2017). 115–133.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @incollection{atzmueller2017collective, author = {Atzmueller, Martin and Becker, Martin and Mueller, Juergen}, booktitle = {Participatory Sensing, Opinions and Collective Awareness}, keywords = {myown}, pages = {115–133}, publisher = {Springer}, title = {Collective Sensing Platforms}, year = 2017 }

  %0 Book Section %1 atzmueller2017collective %A Atzmueller, Martin %A Becker, Martin %A Mueller, Juergen %B Participatory Sensing, Opinions and Collective Awareness %D 2017 %I Springer %P 115--133 %T Collective Sensing Platforms
• 
  Mining social semantics on the social web Hotho, A.; Jaeschke, R.; Lerman, K. in Semantic Web (2017). 8(5) 623–624.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{wrro115871, author = {Hotho, A. and Jaeschke, R. and Lerman, K.}, journal = {Semantic Web}, keywords = {from:hotho}, month = {April}, note = {\copyright 2017 IOS Press and the authors. This is an author produced version of a paper subsequently published in Semantic Web. Uploaded in accordance with the publisher's self-archiving policy.}, number = 5, pages = {623–624}, publisher = {IOS Press}, title = {Mining social semantics on the social web}, volume = 8, year = 2017 }

  %0 Journal Article %1 wrro115871 %A Hotho, A. %A Jaeschke, R. %A Lerman, K. %D 2017 %I IOS Press %J Semantic Web %N 5 %P 623--624 %T Mining social semantics on the social web %U http://eprints.whiterose.ac.uk/115871/ %V 8
• 
  Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson Gravino, Pietro; S{\^\i}rbu, Alina; Becker, Martin; Servedio, Vito DP; Loreto, Vittorio in Participatory Sensing, Opinions and Collective Awareness (2017). 337–362.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @incollection{gravino2017experimental, author = {Gravino, Pietro and S{\^\i}rbu, Alina and Becker, Martin and Servedio, Vito DP and Loreto, Vittorio}, booktitle = {Participatory Sensing, Opinions and Collective Awareness}, keywords = {myown}, pages = {337–362}, publisher = {Springer}, title = {Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson}, year = 2017 }

  %0 Book Section %1 gravino2017experimental %A Gravino, Pietro %A S{\^\i}rbu, Alina %A Becker, Martin %A Servedio, Vito DP %A Loreto, Vittorio %B Participatory Sensing, Opinions and Collective Awareness %D 2017 %I Springer %P 337--362 %T Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson
• 
  MixedTrails: Bayesian hypothesis comparison on heterogeneous sequential data Becker, Martin; Lemmerich, Florian; Singer, Philipp; Strohmaier, Markus; Hotho, Andreas in Data Mining and Knowledge Discovery (2017).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Sequential traces of user data are frequently observed online and offline, e.g., as sequences of visited websites or as sequences of locations captured by GPS. However, understanding factors explaining the production of sequence data is a challenging task, especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of browsing a website or movement behavior may vary between groups of users. In this work, we tackle this task and propose MixedTrails , a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis is derived from existing literature, theory, or intuition and represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions. For example, when trying to understand human movement in a city and given some data, a hypothesis assuming tourists to be more likely to move towards points of interests than locals can be shown to be more plausible than a hypothesis assuming the opposite. Our approach incorporates such hypotheses as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors, give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.

  @article{becker2017mixedtrails, abstract = {Sequential traces of user data are frequently observed online and offline, e.g., as sequences of visited websites or as sequences of locations captured by GPS. However, understanding factors explaining the production of sequence data is a challenging task, especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of browsing a website or movement behavior may vary between groups of users. In this work, we tackle this task and propose MixedTrails , a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis is derived from existing literature, theory, or intuition and represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions. For example, when trying to understand human movement in a city and given some data, a hypothesis assuming tourists to be more likely to move towards points of interests than locals can be shown to be more plausible than a hypothesis assuming the opposite. Our approach incorporates such hypotheses as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors, give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.}, author = {Becker, Martin and Lemmerich, Florian and Singer, Philipp and Strohmaier, Markus and Hotho, Andreas}, journal = {Data Mining and Knowledge Discovery}, keywords = {sequence}, month = {jul}, title = {MixedTrails: Bayesian hypothesis comparison on heterogeneous sequential data}, year = 2017 }

  %0 Journal Article %1 becker2017mixedtrails %A Becker, Martin %A Lemmerich, Florian %A Singer, Philipp %A Strohmaier, Markus %A Hotho, Andreas %D 2017 %J Data Mining and Knowledge Discovery %R 10.1007/s10618-017-0518-x %T MixedTrails: Bayesian hypothesis comparison on heterogeneous sequential data %U http://dx.doi.org/10.1007/s10618-017-0518-x %X Sequential traces of user data are frequently observed online and offline, e.g., as sequences of visited websites or as sequences of locations captured by GPS. However, understanding factors explaining the production of sequence data is a challenging task, especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of browsing a website or movement behavior may vary between groups of users. In this work, we tackle this task and propose MixedTrails , a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis is derived from existing literature, theory, or intuition and represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions. For example, when trying to understand human movement in a city and given some data, a hypothesis assuming tourists to be more likely to move towards points of interests than locals can be shown to be more plausible than a hypothesis assuming the opposite. Our approach incorporates such hypotheses as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors, give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.
• 
  Learning Word Embeddings from Tagging Data: A methodological comparison Niebler, Thomas; Hahn, Luzian; Hotho, Andreas in Proceedings of the LWDA (2017).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{niebler2017learning_2, author = {Niebler, Thomas and Hahn, Luzian and Hotho, Andreas}, booktitle = {Proceedings of the LWDA}, keywords = {word2vec}, title = {Learning Word Embeddings from Tagging Data: A methodological comparison}, year = 2017 }

  %0 Conference Paper %1 niebler2017learning_2 %A Niebler, Thomas %A Hahn, Luzian %A Hotho, Andreas %B Proceedings of the LWDA %D 2017 %T Learning Word Embeddings from Tagging Data: A methodological comparison
• 
  Eleven-Week Preparation Involving Polarized Intensity Distribution Is Not Superior to Pyramidal Distribution in National Elite Rowers Treff, Gunnar; Winkert, Kay; Sareban, Mahdi; Steinacker, Jürgen M.; Becker, Martin; Sperlich, Billy in Frontiers in Physiology (2017). 8 515.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Polarized (POL) training intensity distribution (TID) emphasizes high-volume low-intensity exercise in zone (Z)1 (< first lactate threshold) with a greater proportion of high-intensity Z3 (> second lactate threshold) compared to Z2 (between first and second lactate threshold). In highly trained rowers there is a lack of prospective controlled evidence whether POL is superior to pyramidal (PYR; i.e. greater volume in Z1 vs. Z2 vs. Z3) TID. The aim of the study was to compare the effect of POL vs. PYR TID in rowers during an 11-wk preparation period. Fourteen national elite male rowers participated (age: 20 ± 2 years, maximal oxygen uptake (⩒O2max): 66±5 mL/min/kg). The sample was split into PYR and POL by varying the percentage spent in Z2 and Z3 while Z1 was clamped to ~93% and matched for total and rowing volume. Actual TIDs were based on time within heart rate zones (Z1 and Z2) and duration of Z3-intervals. The main outcome variables were average power in 2000 m ergometer-test (P2000m), power associated with 4 mmol/L [blood lactate] (P4[BLa]), and ⩒O2max. To quantify the level of polarization, we calculated a Polarization-Index as log (%Z1 x %Z3/%Z2). PYR and POL did not significantly differ regarding rowing or total volume, but POL had a higher percentage of Z3 intensities (6±3% vs. 2±1%; p < .005) while Z2 was lower (1±1% vs. 3±2%; p < .05) and Z1 was similar (94±3% vs. 93±2%, p = .37). Consequently, Polarization-Index was significantly higher in POL (3.0±0.7 a.u. vs. 1.9±0.4 a.u.; p < .01) P2000m did not significantly change with PYR (1.5±1.7%, p = .06) nor POL (1.5±2.6%, p = .26). ⩒O2max did not change (1.7±5.6%, p = .52 or 0.6±2.6, p = .67) and a small increase in P4[BLa] was observed in PYR only (1.9±4.8%, p = .37 or -0.5±4.1%, p = .77). Changes from pre to post were not significantly different between groups in any performance measure. POL did not prove to be superior to PYR, possibly due to the high and very similar percentage of Z1 in this study.

  @article{treff2017elevenweek, abstract = {Polarized (POL) training intensity distribution (TID) emphasizes high-volume low-intensity exercise in zone (Z)1 (< first lactate threshold) with a greater proportion of high-intensity Z3 (> second lactate threshold) compared to Z2 (between first and second lactate threshold). In highly trained rowers there is a lack of prospective controlled evidence whether POL is superior to pyramidal (PYR; i.e. greater volume in Z1 vs. Z2 vs. Z3) TID. The aim of the study was to compare the effect of POL vs. PYR TID in rowers during an 11-wk preparation period. Fourteen national elite male rowers participated (age: 20 ± 2 years, maximal oxygen uptake (⩒O2max): 66±5 mL/min/kg). The sample was split into PYR and POL by varying the percentage spent in Z2 and Z3 while Z1 was clamped to  93% and matched for total and rowing volume. Actual TIDs were based on time within heart rate zones (Z1 and Z2) and duration of Z3-intervals. The main outcome variables were average power in 2000 m ergometer-test (P2000m), power associated with 4 mmol/L [blood lactate] (P4[BLa]), and ⩒O2max. To quantify the level of polarization, we calculated a Polarization-Index as log (%Z1 x %Z3/%Z2). PYR and POL did not significantly differ regarding rowing or total volume, but POL had a higher percentage of Z3 intensities (6±3% vs. 2±1%; p < .005) while Z2 was lower (1±1% vs. 3±2%; p < .05) and Z1 was similar (94±3% vs. 93±2%, p = .37). Consequently, Polarization-Index was significantly higher in POL (3.0±0.7 a.u. vs. 1.9±0.4 a.u.; p < .01) P2000m did not significantly change with PYR (1.5±1.7%, p = .06) nor POL (1.5±2.6%, p = .26). ⩒O2max did not change (1.7±5.6%, p = .52 or 0.6±2.6, p = .67) and a small increase in P4[BLa] was observed in PYR only (1.9±4.8%, p = .37 or -0.5±4.1%, p = .77). Changes from pre to post were not significantly different between groups in any performance measure. POL did not prove to be superior to PYR, possibly due to the high and very similar percentage of Z1 in this study.}, author = {Treff, Gunnar and Winkert, Kay and Sareban, Mahdi and Steinacker, Jürgen M. and Becker, Martin and Sperlich, Billy}, journal = {Frontiers in Physiology}, keywords = {from:becker}, pages = 515, title = {Eleven-Week Preparation Involving Polarized Intensity Distribution Is Not Superior to Pyramidal Distribution in National Elite Rowers}, volume = 8, year = 2017 }

  %0 Journal Article %1 treff2017elevenweek %A Treff, Gunnar %A Winkert, Kay %A Sareban, Mahdi %A Steinacker, Jürgen M. %A Becker, Martin %A Sperlich, Billy %D 2017 %J Frontiers in Physiology %P 515 %R 10.3389/fphys.2017.00515 %T Eleven-Week Preparation Involving Polarized Intensity Distribution Is Not Superior to Pyramidal Distribution in National Elite Rowers %U http://journal.frontiersin.org/article/10.3389/fphys.2017.00515 %V 8 %X Polarized (POL) training intensity distribution (TID) emphasizes high-volume low-intensity exercise in zone (Z)1 (< first lactate threshold) with a greater proportion of high-intensity Z3 (> second lactate threshold) compared to Z2 (between first and second lactate threshold). In highly trained rowers there is a lack of prospective controlled evidence whether POL is superior to pyramidal (PYR; i.e. greater volume in Z1 vs. Z2 vs. Z3) TID. The aim of the study was to compare the effect of POL vs. PYR TID in rowers during an 11-wk preparation period. Fourteen national elite male rowers participated (age: 20 ± 2 years, maximal oxygen uptake (⩒O2max): 66±5 mL/min/kg). The sample was split into PYR and POL by varying the percentage spent in Z2 and Z3 while Z1 was clamped to ~93% and matched for total and rowing volume. Actual TIDs were based on time within heart rate zones (Z1 and Z2) and duration of Z3-intervals. The main outcome variables were average power in 2000 m ergometer-test (P2000m), power associated with 4 mmol/L [blood lactate] (P4[BLa]), and ⩒O2max. To quantify the level of polarization, we calculated a Polarization-Index as log (%Z1 x %Z3/%Z2). PYR and POL did not significantly differ regarding rowing or total volume, but POL had a higher percentage of Z3 intensities (6±3% vs. 2±1%; p < .005) while Z2 was lower (1±1% vs. 3±2%; p < .05) and Z1 was similar (94±3% vs. 93±2%, p = .37). Consequently, Polarization-Index was significantly higher in POL (3.0±0.7 a.u. vs. 1.9±0.4 a.u.; p < .01) P2000m did not significantly change with PYR (1.5±1.7%, p = .06) nor POL (1.5±2.6%, p = .26). ⩒O2max did not change (1.7±5.6%, p = .52 or 0.6±2.6, p = .67) and a small increase in P4[BLa] was observed in PYR only (1.9±4.8%, p = .37 or -0.5±4.1%, p = .77). Changes from pre to post were not significantly different between groups in any performance measure. POL did not prove to be superior to PYR, possibly due to the high and very similar percentage of Z1 in this study.
• 
  A Toolset for Intrusion and Insider Threat Detection Ring, Markus; Wunderlich, Sarah; Gr{\"u}dl, Dominik; Landes, Dieter; Hotho, Andreas in Data Analytics and Decision Support for Cybersecurity: Trends, Methodologies and Applications, I. Palomares Carrascosa, H. K. Kalutarage, Y. Huang (eds.) (2017). 3–31.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Company data are a valuable asset and must be protected against unauthorized access and manipulation. In this contribution, we report on our ongoing work that aims to support IT security experts with identifying novel or obfuscated attacks in company networks, irrespective of their origin inside or outside the company network. A new toolset for anomaly based network intrusion detection is proposed. This toolset uses flow-based data which can be easily retrieved by central network components. We study the challenges of analysing flow-based data streams using data mining algorithms and build an appropriate approach step by step. In contrast to previous work, we collect flow-based data for each host over a certain time window, include the knowledge of domain experts and analyse the data from three different views. We argue that incorporating expert knowledge and previous flows allow us to create more meaningful attributes for subsequent analysis methods. This way, we try to detect novel attacks while simultaneously limiting the number of false positives.

  @inbook{Ring2017, abstract = {Company data are a valuable asset and must be protected against unauthorized access and manipulation. In this contribution, we report on our ongoing work that aims to support IT security experts with identifying novel or obfuscated attacks in company networks, irrespective of their origin inside or outside the company network. A new toolset for anomaly based network intrusion detection is proposed. This toolset uses flow-based data which can be easily retrieved by central network components. We study the challenges of analysing flow-based data streams using data mining algorithms and build an appropriate approach step by step. In contrast to previous work, we collect flow-based data for each host over a certain time window, include the knowledge of domain experts and analyse the data from three different views. We argue that incorporating expert knowledge and previous flows allow us to create more meaningful attributes for subsequent analysis methods. This way, we try to detect novel attacks while simultaneously limiting the number of false positives.}, address = {Cham}, author = {Ring, Markus and Wunderlich, Sarah and Gr{\"u}dl, Dominik and Landes, Dieter and Hotho, Andreas}, booktitle = {Data Analytics and Decision Support for Cybersecurity: Trends, Methodologies and Applications}, editor = {Palomares Carrascosa, Iv{\'a}n and Kalutarage, Harsha Kumara and Huang, Yan}, keywords = {security:selected}, pages = {3–31}, publisher = {Springer International Publishing}, title = {A Toolset for Intrusion and Insider Threat Detection}, year = 2017 }

  %0 Book Section %1 Ring2017 %A Ring, Markus %A Wunderlich, Sarah %A Gr{\"u}dl, Dominik %A Landes, Dieter %A Hotho, Andreas %B Data Analytics and Decision Support for Cybersecurity: Trends, Methodologies and Applications %C Cham %D 2017 %E Palomares Carrascosa, Iv{\'a}n %E Kalutarage, Harsha Kumara %E Huang, Yan %I Springer International Publishing %P 3--31 %R 10.1007/978-3-319-59439-2_1 %T A Toolset for Intrusion and Insider Threat Detection %U https://doi.org/10.1007/978-3-319-59439-2_1 %X Company data are a valuable asset and must be protected against unauthorized access and manipulation. In this contribution, we report on our ongoing work that aims to support IT security experts with identifying novel or obfuscated attacks in company networks, irrespective of their origin inside or outside the company network. A new toolset for anomaly based network intrusion detection is proposed. This toolset uses flow-based data which can be easily retrieved by central network components. We study the challenges of analysing flow-based data streams using data mining algorithms and build an appropriate approach step by step. In contrast to previous work, we collect flow-based data for each host over a certain time window, include the knowledge of domain experts and analyse the data from three different views. We argue that incorporating expert knowledge and previous flows allow us to create more meaningful attributes for subsequent analysis methods. This way, we try to detect novel attacks while simultaneously limiting the number of false positives. %@ 978-3-319-59439-2

• 
  What Users Actually do in a Social Tagging System: A Study of User Behavior in BibSonomy Doerfel, Stephan; Zoller, Daniel; Singer, Philipp; Niebler, Thomas; Hotho, Andreas; Strohmaier, Markus in ACM Transactions on the Web (2016). 10(2) 14:1–14:32.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Social tagging systems have established themselves as an important part in today’s web and have attracted the interest of our research community in a variety of investigations. Henceforth, several aspects of social tagging systems have been discussed and assumptions have emerged on which our community builds their work. Yet, testing such assumptions has been difficult due to the absence of suitable usage data in the past. In this work, we thoroughly investigate and evaluate four aspects about tagging systems, covering social interaction, retrieval of posted resources, the importance of the three different types of entities, users, resources, and tags, as well as connections between these entities’ popularity in posted and in requested content. For that purpose, we examine live server log data gathered from the real-world, public social tagging system BibSonomy. Our empirical results paint a mixed picture about the four aspects. While for some, typical assumptions hold to a certain extent, other aspects need to be reflected in a very critical light. Our observations have implications for the understanding of social tagging systems, and the way they are used on the web. We make the dataset used in this work available to other researchers.

  @article{doerfel2016users, abstract = {Social tagging systems have established themselves as an important part in today’s web and have attracted the interest of our research community in a variety of investigations. Henceforth, several aspects of social tagging systems have been discussed and assumptions have emerged on which our community builds their work. Yet, testing such assumptions has been difficult due to the absence of suitable usage data in the past. In this work, we thoroughly investigate and evaluate four aspects about tagging systems, covering social interaction, retrieval of posted resources, the importance of the three different types of entities, users, resources, and tags, as well as connections between these entities’ popularity in posted and in requested content. For that purpose, we examine live server log data gathered from the real-world, public social tagging system BibSonomy. Our empirical results paint a mixed picture about the four aspects. While for some, typical assumptions hold to a certain extent, other aspects need to be reflected in a very critical light. Our observations have implications for the understanding of social tagging systems, and the way they are used on the web. We make the dataset used in this work available to other researchers.}, author = {Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus}, journal = {ACM Transactions on the Web}, keywords = {user}, number = 2, pages = {14:1–14:32}, title = {What Users Actually do in a Social Tagging System: A Study of User Behavior in BibSonomy}, volume = 10, year = 2016 }

  %0 Journal Article %1 doerfel2016users %A Doerfel, Stephan %A Zoller, Daniel %A Singer, Philipp %A Niebler, Thomas %A Hotho, Andreas %A Strohmaier, Markus %D 2016 %J ACM Transactions on the Web %N 2 %P 14:1--14:32 %T What Users Actually do in a Social Tagging System: A Study of User Behavior in BibSonomy %V 10 %X Social tagging systems have established themselves as an important part in today’s web and have attracted the interest of our research community in a variety of investigations. Henceforth, several aspects of social tagging systems have been discussed and assumptions have emerged on which our community builds their work. Yet, testing such assumptions has been difficult due to the absence of suitable usage data in the past. In this work, we thoroughly investigate and evaluate four aspects about tagging systems, covering social interaction, retrieval of posted resources, the importance of the three different types of entities, users, resources, and tags, as well as connections between these entities’ popularity in posted and in requested content. For that purpose, we examine live server log data gathered from the real-world, public social tagging system BibSonomy. Our empirical results paint a mixed picture about the four aspects. While for some, typical assumptions hold to a certain extent, other aspects need to be reflected in a very critical light. Our observations have implications for the understanding of social tagging systems, and the way they are used on the web. We make the dataset used in this work available to other researchers.
• 
  Mining Subgroups with Exceptional Transition Behavior. Lemmerich, Florian; Becker, Martin; Singer, Philipp; Helic, Denis; Hotho, Andreas; Strohmaier, Markus in KDD, B. Krishnapuram, M. Shah, A. J. Smola, C. Aggarwal, D. Shen, R. Rastogi (eds.) (2016). 965–974.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{lemmerich2016mining, author = {Lemmerich, Florian and Becker, Martin and Singer, Philipp and Helic, Denis and Hotho, Andreas and Strohmaier, Markus}, booktitle = {KDD}, crossref = {conf/kdd/2016}, editor = {Krishnapuram, Balaji and Shah, Mohak and Smola, Alexander J. and Aggarwal, Charu and Shen, Dou and Rastogi, Rajeev}, keywords = {subtrails}, pages = {965-974}, publisher = {ACM}, title = {Mining Subgroups with Exceptional Transition Behavior.}, year = 2016 }

  %0 Conference Paper %1 lemmerich2016mining %A Lemmerich, Florian %A Becker, Martin %A Singer, Philipp %A Helic, Denis %A Hotho, Andreas %A Strohmaier, Markus %B KDD %D 2016 %E Krishnapuram, Balaji %E Shah, Mohak %E Smola, Alexander J. %E Aggarwal, Charu %E Shen, Dou %E Rastogi, Rajeev %I ACM %P 965-974 %T Mining Subgroups with Exceptional Transition Behavior. %U http://dblp.uni-trier.de/db/conf/kdd/kdd2016.html#Lemmerich0SHHS16 %@ 978-1-4503-4232-2
• 
  SparkTrails: A MapReduce Implementation of HypTrails for Comparing Hypotheses About Human Trails. Becker, Martin; Mewes, Hauke; Hotho, Andreas; Dimitrov, Dimitar; Lemmerich, Florian; Strohmaier, Markus in WWW (Companion Volume), J. Bourdeau, J. Hendler, R. Nkambou, I. Horrocks, B. Y. Zhao (eds.) (2016). 17–18.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{becker2016sparktrails, author = {Becker, Martin and Mewes, Hauke and Hotho, Andreas and Dimitrov, Dimitar and Lemmerich, Florian and Strohmaier, Markus}, booktitle = {WWW (Companion Volume)}, crossref = {conf/www/2016c}, editor = {Bourdeau, Jacqueline and Hendler, Jim and Nkambou, Roger and Horrocks, Ian and Zhao, Ben Y.}, keywords = {selected}, pages = {17-18}, publisher = {ACM}, title = {SparkTrails: A MapReduce Implementation of HypTrails for Comparing Hypotheses About Human Trails.}, year = 2016 }

  %0 Conference Paper %1 becker2016sparktrails %A Becker, Martin %A Mewes, Hauke %A Hotho, Andreas %A Dimitrov, Dimitar %A Lemmerich, Florian %A Strohmaier, Markus %B WWW (Companion Volume) %D 2016 %E Bourdeau, Jacqueline %E Hendler, Jim %E Nkambou, Roger %E Horrocks, Ian %E Zhao, Ben Y. %I ACM %P 17-18 %T SparkTrails: A MapReduce Implementation of HypTrails for Comparing Hypotheses About Human Trails. %U http://dblp.uni-trier.de/db/conf/www/www2016c.html#0003MHDLS16 %@ 978-1-4503-4144-8
• 
  Extracting Semantics from Random Walks on Wikipedia: Comparing learning and counting methods Dallmann, Alexander; Niebler, Thomas; Lemmerich, Florian; Hotho, Andreas in Wiki Workshop@ICWSM, R. West, L. Zia, D. Taraborelli, J. Leskovec (eds.) (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Semantic relatedness between words has been extracted from a variety of sources. In this ongoing work, we explore and compare several options for determining if semantic relatedness can be extracted from navigation structures in Wikipedia. In that direction, we first investigate the potential of representation learning techniques such as DeepWalk in comparison to previously applied methods based on counting co-occurrences. Since both methods are based on (random) paths in the network, we also study different approaches to generate paths from Wikipedia link structure. For this task, we do not only consider the link structure of Wikipedia, but also actual navigation behavior of users. Finally, we analyze if semantics can also be extracted from smaller subsets of the Wikipedia link network. As a result we find that representa- tion learning techniques mostly outperform the investigated co-occurrence counting methods on the Wikipedia network. However, we find that this is not the case for paths sampled from human navigation behavior.

  @inproceedings{dallmann2016extracting, abstract = {Semantic relatedness between words has been extracted from a variety of sources. In this ongoing work, we explore and compare several options for determining if semantic relatedness can be extracted from navigation structures in Wikipedia. In that direction, we first investigate the potential of representation learning techniques such as DeepWalk in comparison to previously applied methods based on counting co-occurrences. Since both methods are based on (random) paths in the network, we also study different approaches to generate paths from Wikipedia link structure. For this task, we do not only consider the link structure of Wikipedia, but also actual navigation behavior of users. Finally, we analyze if semantics can also be extracted from smaller subsets of the Wikipedia link network. As a result we find that representa- tion learning techniques mostly outperform the investigated co-occurrence counting methods on the Wikipedia network. However, we find that this is not the case for paths sampled from human navigation behavior.}, author = {Dallmann, Alexander and Niebler, Thomas and Lemmerich, Florian and Hotho, Andreas}, booktitle = {Wiki Workshop@ICWSM}, editor = {West, Robert and Zia, Leila and Taraborelli, Dario and Leskovec, Jure}, keywords = {word2vec}, title = {Extracting Semantics from Random Walks on Wikipedia: Comparing learning and counting methods}, year = 2016 }

  %0 Conference Paper %1 dallmann2016extracting %A Dallmann, Alexander %A Niebler, Thomas %A Lemmerich, Florian %A Hotho, Andreas %B Wiki Workshop@ICWSM %D 2016 %E West, Robert %E Zia, Leila %E Taraborelli, Dario %E Leskovec, Jure %T Extracting Semantics from Random Walks on Wikipedia: Comparing learning and counting methods %U http://snap.stanford.edu/wikiworkshop2016/papers/wikiworkshop_icwsm2016_dallmann.pdf %X Semantic relatedness between words has been extracted from a variety of sources. In this ongoing work, we explore and compare several options for determining if semantic relatedness can be extracted from navigation structures in Wikipedia. In that direction, we first investigate the potential of representation learning techniques such as DeepWalk in comparison to previously applied methods based on counting co-occurrences. Since both methods are based on (random) paths in the network, we also study different approaches to generate paths from Wikipedia link structure. For this task, we do not only consider the link structure of Wikipedia, but also actual navigation behavior of users. Finally, we analyze if semantics can also be extracted from smaller subsets of the Wikipedia link network. As a result we find that representa- tion learning techniques mostly outperform the investigated co-occurrence counting methods on the Wikipedia network. However, we find that this is not the case for paths sampled from human navigation behavior.
• 
  FolkTrails: Interpreting Navigation Behavior in a Social Tagging System Niebler, Thomas; Becker, Martin; Zoller, Daniel; Doerfel, Stephan; Hotho, Andreas in Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, CIKM ’16 (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users’ needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.

  @inproceedings{niebler2016folktrails, abstract = {Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users’ needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.}, address = {New York, NY, USA}, author = {Niebler, Thomas and Becker, Martin and Zoller, Daniel and Doerfel, Stephan and Hotho, Andreas}, booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management}, keywords = {tagging}, publisher = {ACM}, series = {CIKM '16}, title = {FolkTrails: Interpreting Navigation Behavior in a Social Tagging System}, year = 2016 }

  %0 Conference Paper %1 niebler2016folktrails %A Niebler, Thomas %A Becker, Martin %A Zoller, Daniel %A Doerfel, Stephan %A Hotho, Andreas %B Proceedings of the 25th ACM International on Conference on Information and Knowledge Management %C New York, NY, USA %D 2016 %I ACM %R 10.1145/2983323.2983686 %T FolkTrails: Interpreting Navigation Behavior in a Social Tagging System %X Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users’ needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.
• 
  Prediction of Happy Endings in German Novels Zehe, Albin; Becker, Martin; Hettinger, Lena; Hotho, Andreas; Reger, Isabella; Jannidis, Fotis in Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016, P. Cellier, T. Charnois, A. Hotho, S. Matwin, M.-F. Moens, Y. Toussaint (eds.) (2016). 9–16.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73%.

  @inproceedings{zehe2016prediction, abstract = {Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73%.}, author = {Zehe, Albin and Becker, Martin and Hettinger, Lena and Hotho, Andreas and Reger, Isabella and Jannidis, Fotis}, booktitle = {Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016}, editor = {Cellier, Peggy and Charnois, Thierry and Hotho, Andreas and Matwin, Stan and Moens, Marie-Francine and Toussaint, Yannick}, keywords = {sentiment}, month = {jul}, pages = {9-16}, title = {Prediction of Happy Endings in German Novels}, year = 2016 }

  %0 Conference Paper %1 zehe2016prediction %A Zehe, Albin %A Becker, Martin %A Hettinger, Lena %A Hotho, Andreas %A Reger, Isabella %A Jannidis, Fotis %B Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016 %D 2016 %E Cellier, Peggy %E Charnois, Thierry %E Hotho, Andreas %E Matwin, Stan %E Moens, Marie-Francine %E Toussaint, Yannick %P 9-16 %T Prediction of Happy Endings in German Novels %U http://ceur-ws.org/Vol-1646/ %X Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73%.
• 
  Extracting Semantics from Unconstrained Navigation on Wikipedia Niebler, Thomas; Schlör, Daniel; Becker, Martin; Hotho, Andreas in KI (2016). 30(2) 163–168.
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @article{journals/ki/NieblerS0H16, author = {Niebler, Thomas and Schlör, Daniel and Becker, Martin and Hotho, Andreas}, journal = {KI}, keywords = {wikipedia}, number = 2, pages = {163-168}, title = {Extracting Semantics from Unconstrained Navigation on Wikipedia}, volume = 30, year = 2016 }

  %0 Journal Article %1 journals/ki/NieblerS0H16 %A Niebler, Thomas %A Schlör, Daniel %A Becker, Martin %A Hotho, Andreas %D 2016 %J KI %N 2 %P 163-168 %T Extracting Semantics from Unconstrained Navigation on Wikipedia %U http://dblp.uni-trier.de/db/journals/ki/ki30.html#NieblerS0H16 %V 30
• 
  Comparison of non-invasive individual monitoring of the training and health of athletes with commercially available wearable technologies Düking, Peter; Hotho, Andreas; Fuss, Franz Konstantin; Holmberg, Hans-Christer; Sperlich, Billy in Frontiers in Physiology (2016). 7(71)
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Athletes adapt their training daily to optimize performance, as well as avoid fatigue, overtraining and other undesirable effects on their health. To optimize training load, each athlete must take his/her own personal objective and subjective characteristics into consideration and an increasing number of wearable technologies (wearables) provide convenient monitoring of various parameters. Accordingly, it is important to help athletes decide which parameters are of primary interest and which wearables can monitor these parameters most effectively. Here, we discuss the wearable technologies available for non-invasive monitoring of various parameters concerning an athlete's training and health. On the basis of these considerations, we suggest directions for future development. Furthermore, we propose that a combination of several wearables is most effective for accessing all relevant parameters, disturbing the athlete as little as possible, and optimizing performance and promoting health.

  @article{10.3389/fphys.2016.00071, abstract = {Athletes adapt their training daily to optimize performance, as well as avoid fatigue, overtraining and other undesirable effects on their health. To optimize training load, each athlete must take his/her own personal objective and subjective characteristics into consideration and an increasing number of wearable technologies (wearables) provide convenient monitoring of various parameters. Accordingly, it is important to help athletes decide which parameters are of primary interest and which wearables can monitor these parameters most effectively. Here, we discuss the wearable technologies available for non-invasive monitoring of various parameters concerning an athlete's training and health. On the basis of these considerations, we suggest directions for future development. Furthermore, we propose that a combination of several wearables is most effective for accessing all relevant parameters, disturbing the athlete as little as possible, and optimizing performance and promoting health.}, author = {Düking, Peter and Hotho, Andreas and Fuss, Franz Konstantin and Holmberg, Hans-Christer and Sperlich, Billy}, journal = {Frontiers in Physiology}, keywords = {wearable}, number = 71, title = {Comparison of non-invasive individual monitoring of the training and health of athletes with commercially available wearable technologies}, volume = 7, year = 2016 }

  %0 Journal Article %1 10.3389/fphys.2016.00071 %A Düking, Peter %A Hotho, Andreas %A Fuss, Franz Konstantin %A Holmberg, Hans-Christer %A Sperlich, Billy %D 2016 %J Frontiers in Physiology %N 71 %R 10.3389/fphys.2016.00071 %T Comparison of non-invasive individual monitoring of the training and health of athletes with commercially available wearable technologies %U http://www.frontiersin.org/exercise_physiology/10.3389/fphys.2016.00071/abstract %V 7 %X Athletes adapt their training daily to optimize performance, as well as avoid fatigue, overtraining and other undesirable effects on their health. To optimize training load, each athlete must take his/her own personal objective and subjective characteristics into consideration and an increasing number of wearable technologies (wearables) provide convenient monitoring of various parameters. Accordingly, it is important to help athletes decide which parameters are of primary interest and which wearables can monitor these parameters most effectively. Here, we discuss the wearable technologies available for non-invasive monitoring of various parameters concerning an athlete's training and health. On the basis of these considerations, we suggest directions for future development. Furthermore, we propose that a combination of several wearables is most effective for accessing all relevant parameters, disturbing the athlete as little as possible, and optimizing performance and promoting health.
• 
  Posted, Visited, Exported: Altmetrics in the Social Tagging System BibSonomy Zoller, Daniel; Doerfel, Stephan; Jäschke, Robert; Stumme, Gerd; Hotho, Andreas in Journal of Informetrics (2016). 10(3) 732–749.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  In social tagging systems, like Mendeley, CiteULike, and BibSonomy, users can post, tag, visit, or export scholarly publications. In this paper, we compare citations with metrics derived from users’ activities (altmetrics) in the popular social bookmarking system BibSonomy. Our analysis, using a corpus of more than 250,000 publications published before 2010, reveals that overall, citations and altmetrics in BibSonomy are mildly correlated. Furthermore, grouping publications by user-generated tags results in topic-homogeneous subsets that exhibit higher correlations with citations than the full corpus. We find that posts, exports, and visits of publications are correlated with citations and even bear predictive power over future impact. Machine learning classifiers predict whether the number of citations that a publication receives in a year exceeds the median number of citations in that year, based on the usage counts of the preceding year. In that setup, a Random Forest predictor outperforms the baseline on average by seven percentage points.

  @article{zoller2016posted, abstract = {In social tagging systems, like Mendeley, CiteULike, and BibSonomy, users can post, tag, visit, or export scholarly publications. In this paper, we compare citations with metrics derived from users’ activities (altmetrics) in the popular social bookmarking system BibSonomy. Our analysis, using a corpus of more than 250,000 publications published before 2010, reveals that overall, citations and altmetrics in BibSonomy are mildly correlated. Furthermore, grouping publications by user-generated tags results in topic-homogeneous subsets that exhibit higher correlations with citations than the full corpus. We find that posts, exports, and visits of publications are correlated with citations and even bear predictive power over future impact. Machine learning classifiers predict whether the number of citations that a publication receives in a year exceeds the median number of citations in that year, based on the usage counts of the preceding year. In that setup, a Random Forest predictor outperforms the baseline on average by seven percentage points.}, author = {Zoller, Daniel and Doerfel, Stephan and Jäschke, Robert and Stumme, Gerd and Hotho, Andreas}, journal = {Journal of Informetrics}, keywords = {tagging}, number = 3, pages = {732–749}, title = {Posted, Visited, Exported: Altmetrics in the Social Tagging System BibSonomy}, volume = 10, year = 2016 }

  %0 Journal Article %1 zoller2016posted %A Zoller, Daniel %A Doerfel, Stephan %A Jäschke, Robert %A Stumme, Gerd %A Hotho, Andreas %D 2016 %J Journal of Informetrics %N 3 %P 732--749 %T Posted, Visited, Exported: Altmetrics in the Social Tagging System BibSonomy %V 10 %X In social tagging systems, like Mendeley, CiteULike, and BibSonomy, users can post, tag, visit, or export scholarly publications. In this paper, we compare citations with metrics derived from users’ activities (altmetrics) in the popular social bookmarking system BibSonomy. Our analysis, using a corpus of more than 250,000 publications published before 2010, reveals that overall, citations and altmetrics in BibSonomy are mildly correlated. Furthermore, grouping publications by user-generated tags results in topic-homogeneous subsets that exhibit higher correlations with citations than the full corpus. We find that posts, exports, and visits of publications are correlated with citations and even bear predictive power over future impact. Machine learning classifiers predict whether the number of citations that a publication receives in a year exceeds the median number of citations in that year, based on the usage counts of the preceding year. In that setup, a Random Forest predictor outperforms the baseline on average by seven percentage points.
• 
  Straight Talk! Automatic Recognition of Direct Speech in Nineteenth-Century French Novels. Sch{\"o}ch, Christof; Schl{\"o}r, Daniel; Popp, Stefanie; Brunner, Annelen; Henny, Ulrike; Tello, Jos{\’e} Calvo in DH (2016). 346–353.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{schoch2016straight, author = {Sch{\"o}ch, Christof and Schl{\"o}r, Daniel and Popp, Stefanie and Brunner, Annelen and Henny, Ulrike and Tello, Jos{\'e} Calvo}, booktitle = {DH}, keywords = {from:daschloer}, pages = {346–353}, title = {Straight Talk! Automatic Recognition of Direct Speech in Nineteenth-Century French Novels.}, year = 2016 }

  %0 Conference Paper %1 schoch2016straight %A Sch{\"o}ch, Christof %A Schl{\"o}r, Daniel %A Popp, Stefanie %A Brunner, Annelen %A Henny, Ulrike %A Tello, Jos{\'e} Calvo %B DH %D 2016 %P 346--353 %T Straight Talk! Automatic Recognition of Direct Speech in Nineteenth-Century French Novels.
• 
  Analyzing Features for the Detection of Happy Endings in German Novels Jannidis, Fotis; Reger, Isabella; Zehe, Albin; Becker, Martin; Hettinger, Lena; Hotho, Andreas (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels. Its focus lies on the investigation of previously proposed sentiment features in order to gain insight about the relevance of specific features on the one hand and the implications of their performance on the other hand. Therefore, we study various partitionings of novels, considering the highly variable concept of "ending". We also show that our approach, even though still rather simple, can potentially lead to substantial findings relevant to literary studies.

  @misc{jannidis2016analyzing, abstract = {With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels. Its focus lies on the investigation of previously proposed sentiment features in order to gain insight about the relevance of specific features on the one hand and the implications of their performance on the other hand. Therefore, we study various partitionings of novels, considering the highly variable concept of "ending". We also show that our approach, even though still rather simple, can potentially lead to substantial findings relevant to literary studies.}, author = {Jannidis, Fotis and Reger, Isabella and Zehe, Albin and Becker, Martin and Hettinger, Lena and Hotho, Andreas}, keywords = {sentimentanalysis}, note = {cite arxiv:1611.09028}, title = {Analyzing Features for the Detection of Happy Endings in German Novels}, year = 2016 }

  %0 Generic %1 jannidis2016analyzing %A Jannidis, Fotis %A Reger, Isabella %A Zehe, Albin %A Becker, Martin %A Hettinger, Lena %A Hotho, Andreas %D 2016 %T Analyzing Features for the Detection of Happy Endings in German Novels %U http://arxiv.org/abs/1611.09028 %X With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels. Its focus lies on the investigation of previously proposed sentiment features in order to gain insight about the relevance of specific features on the one hand and the implications of their performance on the other hand. Therefore, we study various partitionings of novels, considering the highly variable concept of "ending". We also show that our approach, even though still rather simple, can potentially lead to substantial findings relevant to literary studies.
• 
  MixedTrails: Bayesian Hypotheses Comparison on Heterogeneous Sequential Data Becker, Martin; Lemmerich, Florian; Singer, Philipp; Strohmaier, Markus; Hotho, Andreas (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  Sequential traces of user data are frequently observed online and offline, e.g.,as sequences of visited websites or as sequences of locations captured by GPS. However,understanding factors explaining the production of sequence data is a challenging task,especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of a website visit, or movement behavior may vary between groups of user. In this work, we tackle this task and propose MixedTrails, a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions.For example, when trying to understand human movement in a city, a hypothesis assuming tourists to be more likely to move towards points of interests than locals, can be shown to be more plausible with observed data than a hypothesis assuming the opposite. Our approach incorporates these beliefs as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors,give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.

  @misc{becker2016mixedtrails, abstract = {Sequential traces of user data are frequently observed online and offline, e.g.,as sequences of visited websites or as sequences of locations captured by GPS. However,understanding factors explaining the production of sequence data is a challenging task,especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of a website visit, or movement behavior may vary between groups of user. In this work, we tackle this task and propose MixedTrails, a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions.For example, when trying to understand human movement in a city, a hypothesis assuming tourists to be more likely to move towards points of interests than locals, can be shown to be more plausible with observed data than a hypothesis assuming the opposite. Our approach incorporates these beliefs as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors,give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.}, author = {Becker, Martin and Lemmerich, Florian and Singer, Philipp and Strohmaier, Markus and Hotho, Andreas}, keywords = {sequential}, note = {cite arxiv:1612.07612}, title = {MixedTrails: Bayesian Hypotheses Comparison on Heterogeneous Sequential Data}, year = 2016 }

  %0 Generic %1 becker2016mixedtrails %A Becker, Martin %A Lemmerich, Florian %A Singer, Philipp %A Strohmaier, Markus %A Hotho, Andreas %D 2016 %T MixedTrails: Bayesian Hypotheses Comparison on Heterogeneous Sequential Data %U http://arxiv.org/abs/1612.07612 %X Sequential traces of user data are frequently observed online and offline, e.g.,as sequences of visited websites or as sequences of locations captured by GPS. However,understanding factors explaining the production of sequence data is a challenging task,especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of a website visit, or movement behavior may vary between groups of user. In this work, we tackle this task and propose MixedTrails, a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions.For example, when trying to understand human movement in a city, a hypothesis assuming tourists to be more likely to move towards points of interests than locals, can be shown to be more plausible with observed data than a hypothesis assuming the opposite. Our approach incorporates these beliefs as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors,give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.
• 
  Creation of Specific Flow-Based Training Data Sets for Usage Behaviour Classification Otto, Florian; Ring, Markus; Landes, Dieter; Hotho, Andreas in ECCWS2016-Proceedings fo the 15th European Conference on Cyber Warfare and Security (2016). 437.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{otto2016creation, author = {Otto, Florian and Ring, Markus and Landes, Dieter and Hotho, Andreas}, booktitle = {ECCWS2016-Proceedings fo the 15th European Conference on Cyber Warfare and Security}, keywords = {usage}, organization = {Academic Conferences and publishing limited}, pages = 437, title = {Creation of Specific Flow-Based Training Data Sets for Usage Behaviour Classification}, year = 2016 }

  %0 Conference Paper %1 otto2016creation %A Otto, Florian %A Ring, Markus %A Landes, Dieter %A Hotho, Andreas %B ECCWS2016-Proceedings fo the 15th European Conference on Cyber Warfare and Security %D 2016 %P 437 %T Creation of Specific Flow-Based Training Data Sets for Usage Behaviour Classification
• 
  Classification of Literary Subgenres Hettinger, Lena; Jannidis, Fotis; Reger, Isabella; Hotho, Andreas in DHd 2016 (2016).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{hettinger2016classification, author = {Hettinger, Lena and Jannidis, Fotis and Reger, Isabella and Hotho, Andreas}, booktitle = {DHd 2016}, keywords = {novels}, title = {Classification of Literary Subgenres}, year = 2016 }

  %0 Conference Paper %1 hettinger2016classification %A Hettinger, Lena %A Jannidis, Fotis %A Reger, Isabella %A Hotho, Andreas %B DHd 2016 %D 2016 %T Classification of Literary Subgenres
• 
  Significance Testing for the Classification of Literary Subgenres Hettinger, Lena; Jannidis, Fotis; Reger, Isabella; Hotho, Andreas in DH 2016 (2016).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{hettinger2016significance, author = {Hettinger, Lena and Jannidis, Fotis and Reger, Isabella and Hotho, Andreas}, booktitle = {DH 2016}, keywords = {statistics}, title = {Significance Testing for the Classification of Literary Subgenres}, year = 2016 }

  %0 Conference Paper %1 hettinger2016significance %A Hettinger, Lena %A Jannidis, Fotis %A Reger, Isabella %A Hotho, Andreas %B DH 2016 %D 2016 %T Significance Testing for the Classification of Literary Subgenres

• 
  Participatory Patterns in an International Air Quality Monitoring Initiative Sîrbu, Alina; Becker, Martin; Caminiti, Saverio; De Baets, Bernard; Elen, Bart; Francis, Louise; Gravino, Pietro; Hotho, Andreas; Ingarra, Stefano; Loreto, Vittorio; Molino, Andrea; Mueller, Juergen; Peters, Jan; Ricchiuti, Ferdinando; Saracino, Fabio; Servedio, Vito D. P.; Stumme, Gerd; Theunis, Jan; Tria, Francesca; Van den Bossche, Joris in PLoS ONE (2015). 10(8) e0136763.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  <p>The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.</p>

  @article{10.1371/journal.pone.0136763, abstract = {<p>The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.</p>}, author = {Sîrbu, Alina and Becker, Martin and Caminiti, Saverio and De Baets, Bernard and Elen, Bart and Francis, Louise and Gravino, Pietro and Hotho, Andreas and Ingarra, Stefano and Loreto, Vittorio and Molino, Andrea and Mueller, Juergen and Peters, Jan and Ricchiuti, Ferdinando and Saracino, Fabio and Servedio, Vito D. P. and Stumme, Gerd and Theunis, Jan and Tria, Francesca and Van den Bossche, Joris}, journal = {PLoS ONE}, keywords = {quality}, month = {08}, number = 8, pages = {e0136763}, publisher = {Public Library of Science}, title = {Participatory Patterns in an International Air Quality Monitoring Initiative}, volume = 10, year = 2015 }

  %0 Journal Article %1 10.1371/journal.pone.0136763 %A Sîrbu, Alina %A Becker, Martin %A Caminiti, Saverio %A De Baets, Bernard %A Elen, Bart %A Francis, Louise %A Gravino, Pietro %A Hotho, Andreas %A Ingarra, Stefano %A Loreto, Vittorio %A Molino, Andrea %A Mueller, Juergen %A Peters, Jan %A Ricchiuti, Ferdinando %A Saracino, Fabio %A Servedio, Vito D. P. %A Stumme, Gerd %A Theunis, Jan %A Tria, Francesca %A Van den Bossche, Joris %D 2015 %I Public Library of Science %J PLoS ONE %N 8 %P e0136763 %R 10.1371/journal.pone.0136763 %T Participatory Patterns in an International Air Quality Monitoring Initiative %U http://dx.doi.org/10.1371%2Fjournal.pone.0136763 %V 10 %X <p>The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.</p>
• 
  Exploratory subgroup analytics on ubiquitous data Atzmueller, Martin; Mueller, Juergen; Becker, Martin in Mining, Modeling and Recommending ’Things’ in Social Media (2015). (Vol. 8940) 1–20.
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @incollection{atzmueller2015exploratory, author = {Atzmueller, Martin and Mueller, Juergen and Becker, Martin}, booktitle = {Mining, Modeling and Recommending 'Things' in Social Media}, keywords = {from:becker}, pages = {1–20}, series = {Lecture Notes in Computer Science}, title = {Exploratory subgroup analytics on ubiquitous data}, volume = 8940, year = 2015 }

  %0 Book Section %1 atzmueller2015exploratory %A Atzmueller, Martin %A Mueller, Juergen %A Becker, Martin %B Mining, Modeling and Recommending 'Things' in Social Media %D 2015 %P 1--20 %T Exploratory subgroup analytics on ubiquitous data %V 8940
• 
  Genre classification on German novels Hettinger, Lena; Becker, Martin; Reger, Isabella; Jannidis, Fotis; Hotho, Andreas in Proceedings of the 12th International Workshop on Text-based Information Retrieval (2015).
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  • [ Download ]
  @inproceedings{schwemmlein2015genre, author = {Hettinger, Lena and Becker, Martin and Reger, Isabella and Jannidis, Fotis and Hotho, Andreas}, booktitle = {Proceedings of the 12th International Workshop on Text-based Information Retrieval}, keywords = {novels}, title = {Genre classification on German novels}, year = 2015 }

  %0 Conference Paper %1 schwemmlein2015genre %A Hettinger, Lena %A Becker, Martin %A Reger, Isabella %A Jannidis, Fotis %A Hotho, Andreas %B Proceedings of the 12th International Workshop on Text-based Information Retrieval %D 2015 %T Genre classification on German novels %U http://www.uni-weimar.de/medien/webis/events/tir-15/tir15-papers-final/Hettinger2015-tir-paper.pdf
• 
  Photowalking the city: comparing hypotheses about urban photo trails on Flickr Becker, Martin; Singer, Philipp; Lemmerich, Florian; Hotho, Andreas; Helic, Denis; Strohmaier, Markus in Proceedings of the 7th International Conference on SocialInformatics (to appear) (2015).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{becker2015photowalking, address = {Beijing, China}, author = {Becker, Martin and Singer, Philipp and Lemmerich, Florian and Hotho, Andreas and Helic, Denis and Strohmaier, Markus}, booktitle = {Proceedings of the 7th International Conference on SocialInformatics (to appear)}, keywords = {urban}, month = {dec}, title = {Photowalking the city: comparing hypotheses about urban photo trails on Flickr}, type = {Publication}, year = 2015 }

  %0 Conference Paper %1 becker2015photowalking %A Becker, Martin %A Singer, Philipp %A Lemmerich, Florian %A Hotho, Andreas %A Helic, Denis %A Strohmaier, Markus %B Proceedings of the 7th International Conference on SocialInformatics (to appear) %C Beijing, China %D 2015 %T Photowalking the city: comparing hypotheses about urban photo trails on Flickr
• 
  Evaluating Emergent Semantics in Folksonomies on Human Intuition Niebler, Thomas; Becker, Martin; Zoller, Daniel; Doerfel, Stephan; Hotho, Andreas (2015).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @techreport{tr_niebler2015evaluating, author = {Niebler, Thomas and Becker, Martin and Zoller, Daniel and Doerfel, Stephan and Hotho, Andreas}, keywords = {wordnet}, title = {Evaluating Emergent Semantics in Folksonomies on Human Intuition}, year = 2015 }

  %0 Report %1 tr_niebler2015evaluating %A Niebler, Thomas %A Becker, Martin %A Zoller, Daniel %A Doerfel, Stephan %A Hotho, Andreas %D 2015 %T Evaluating Emergent Semantics in Folksonomies on Human Intuition
• 
  Participatory Patterns in an International Air Quality Monitoring Initiative Sîrbu, Alina; Becker, Martin; Caminiti, Saverio; De Baets, Bernard; Elen, Bart; Francis, Louise; Gravino, Pietro; Hotho, Andreas; Ingarra, Stefano; Loreto, Vittorio; Molino, Andrea; Mueller, Juergen; Peters, Jan; Ricchiuti, Ferdinando; Saracino, Fabio; Servedio, Vito D. P.; Stumme, Gerd; Theunis, Jan; Tria, Francesca; Van den Bossche, Joris (2015).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ URL ]
  The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.

  @misc{sirbu2015participatory, abstract = {The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.}, author = {Sîrbu, Alina and Becker, Martin and Caminiti, Saverio and De Baets, Bernard and Elen, Bart and Francis, Louise and Gravino, Pietro and Hotho, Andreas and Ingarra, Stefano and Loreto, Vittorio and Molino, Andrea and Mueller, Juergen and Peters, Jan and Ricchiuti, Ferdinando and Saracino, Fabio and Servedio, Vito D. P. and Stumme, Gerd and Theunis, Jan and Tria, Francesca and Van den Bossche, Joris}, keywords = {myown}, note = {cite arxiv:1503.07730Comment: 17 pages, 6 figures, 1 supplementary file}, title = {Participatory Patterns in an International Air Quality Monitoring Initiative}, year = 2015 }

  %0 Generic %1 sirbu2015participatory %A Sîrbu, Alina %A Becker, Martin %A Caminiti, Saverio %A De Baets, Bernard %A Elen, Bart %A Francis, Louise %A Gravino, Pietro %A Hotho, Andreas %A Ingarra, Stefano %A Loreto, Vittorio %A Molino, Andrea %A Mueller, Juergen %A Peters, Jan %A Ricchiuti, Ferdinando %A Saracino, Fabio %A Servedio, Vito D. P. %A Stumme, Gerd %A Theunis, Jan %A Tria, Francesca %A Van den Bossche, Joris %D 2015 %T Participatory Patterns in an International Air Quality Monitoring Initiative %U http://arxiv.org/abs/1503.07730 %X The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.
• 
  Media Bias in German Online Newspapers Dallmann, Alexander; Lemmerich, Florian; Zoller, Daniel; Hotho, Andreas in 26th ACM Conference on Hypertext and Social Media (2015).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @inproceedings{dallmann2015media, address = {Cyprus, Turkey, September 1-4}, author = {Dallmann, Alexander and Lemmerich, Florian and Zoller, Daniel and Hotho, Andreas}, booktitle = {26th ACM Conference on Hypertext and Social Media}, keywords = {from:hotho}, publisher = {ACM}, title = {Media Bias in German Online Newspapers}, year = 2015 }

  %0 Conference Paper %1 dallmann2015media %A Dallmann, Alexander %A Lemmerich, Florian %A Zoller, Daniel %A Hotho, Andreas %B 26th ACM Conference on Hypertext and Social Media %C Cyprus, Turkey, September 1-4 %D 2015 %I ACM %T Media Bias in German Online Newspapers
• 
  Hyptrails: A bayesian approach for comparing hypotheses about human trails Singer, P.; Helic, D.; Hotho, A.; Strohmaier, M. in 24th International World Wide Web Conference (WWW2015) (2015).
  • [ BibTeX ]
  • [ EndNote ]
  • [