Daniel Zoller, M.Sc.

Chair of Data Science (Informatik X)
University of Würzburg
Am Hubland
97074 Würzburg
Germany

Viel zu früh verstarb unser Freund und Kollege Daniel Zoller am 05.10.21 nach schwerer Krankheit.

Research Interests

After I received my masters degree in computer science from the University of Kassel in 2013, I started my PhD here at the Data Science Chair. I am interested in recommender systems and information retrieval. Further topics of interest include deep learning, machine learning in general and software engineering.

I am leading the development team of our bookmarking system BibSonomy.

Publications

Here is a list of selected publications I have co-authored. A full list of my publications can be found here.

Doerfel, S., Zoller, D., Singer, P., Niebler, T., Hotho, A., Strohmaier, M.: How Social is Social Tagging?. 23rd International World Wide Web Conference, {WWW} ’14, Seoul, Republic of Korea, April 7-11, 2014, Companion Volume. pp. 251–252. ACM, New York, NY, USA (2014).
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ DOI ]
- [ Download ]
Social tagging systems have established themselves as an important part in today’s web and have attracted the inter- est of our research community in a variety of investigations. This has led to several assumptions about tagging, such as that tagging systems exhibit a social component. In this work we overcome the previous absence of data for testing such an assumption. We thoroughly study social interac- tion, leveraging for the first time live log data gathered from the real-world public social tagging system BibSonomy. Our results indicate that sharing of resources constitutes an im- portant and indeed social aspect of tagging.

@inproceedings{doerfel2014social, abstract = {Social tagging systems have established themselves as an important part in today’s web and have attracted the inter- est of our research community in a variety of investigations. This has led to several assumptions about tagging, such as that tagging systems exhibit a social component. In this work we overcome the previous absence of data for testing such an assumption. We thoroughly study social interac- tion, leveraging for the first time live log data gathered from the real-world public social tagging system BibSonomy. Our results indicate that sharing of resources constitutes an im- portant and indeed social aspect of tagging.}, address = {New York, NY, USA}, author = {Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus}, booktitle = {23rd International World Wide Web Conference, {WWW} '14, Seoul, Republic of Korea, April 7-11, 2014, Companion Volume}, keywords = {selected}, pages = {251–252}, publisher = {ACM}, series = {WWW 2014}, title = {How Social is Social Tagging?}, year = 2014 }
Fischer, E., Zoller, D., Dallmann, A., Hotho, A.: Integrating Keywords into BERT4Rec for Sequential Recommendation. KI 2020: Advances in Artificial Intelligence (2020).
- [ Abstract ]
- [ BibTeX ]
- [ DOI ]
- [ Download ]
A crucial part of recommender systems is to model the user’s preference based on her previous interactions. Different neural networks (e.g., Recurrent Neural Networks), that predict the next item solely based on the sequence of interactions have been successfully applied to sequential recommendation. Recently, BERT4Rec has been proposed, which adapts the BERT architecture based on the Transformer model and training methods used in the Neural Language Modeling community to this task. However, BERT4Rec still only relies on item identifiers to model the user preference, ignoring other sources of information. Therefore, as a first step to include additional information, we propose KeBERT4Rec, a modification of BERT4Rec, which utilizes keyword descriptions of items. We compare two variants for adding keywords to the model on two datasets, a Movielens dataset and a dataset of an online fashion store. First results show that both versions of our model improves the sequential recommending task compared to BERT4Rec.

@inproceedings{fischer2020integrating, abstract = {A crucial part of recommender systems is to model the user’s preference based on her previous interactions. Different neural networks (e.g., Recurrent Neural Networks), that predict the next item solely based on the sequence of interactions have been successfully applied to sequential recommendation. Recently, BERT4Rec has been proposed, which adapts the BERT architecture based on the Transformer model and training methods used in the Neural Language Modeling community to this task. However, BERT4Rec still only relies on item identifiers to model the user preference, ignoring other sources of information. Therefore, as a first step to include additional information, we propose KeBERT4Rec, a modification of BERT4Rec, which utilizes keyword descriptions of items. We compare two variants for adding keywords to the model on two datasets, a Movielens dataset and a dataset of an online fashion store. First results show that both versions of our model improves the sequential recommending task compared to BERT4Rec.}, author = {Fischer, Elisabeth and Zoller, Daniel and Dallmann, Alexander and Hotho, Andreas}, booktitle = {KI 2020: Advances in Artificial Intelligence}, keywords = {selected}, title = {Integrating Keywords into BERT4Rec for Sequential Recommendation}, year = 2020 }
Zoller, D., Doerfel, S., Pölitz, C., Hotho, A.: Leveraging User-Interactions for Time-Aware Tag Recommendations. Proceedings of the Workshop on Temporal Reasoning in Recommender Systems (2017).
- [ Abstract ]
- [ BibTeX ]
- [ 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 = {selected}, series = {{CEUR} Workshop Proceedings}, title = {Leveraging User-Interactions for Time-Aware Tag Recommendations}, year = 2017 }
Zoller, D., Doerfel, S., Jäschke, R., Stumme, G., Hotho, A.: Posted, Visited, Exported: Altmetrics in the Social Tagging System BibSonomy. Journal of Informetrics. 10, 732–749 (2016).
- [ Abstract ]
- [ BibTeX ]
- [ 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 = {selected}, number = 3, pages = {732–749}, title = {Posted, Visited, Exported: Altmetrics in the Social Tagging System BibSonomy}, volume = 10, year = 2016 }
Doerfel, S., Zoller, D., Singer, P., Niebler, T., Hotho, A., Strohmaier, M.: What Users Actually do in a Social Tagging System: A Study of User Behavior in BibSonomy. ACM Transactions on the Web. 10, 14:1–14:32 (2016).
- [ Abstract ]
- [ BibTeX ]
- [ DOI ]
- [ 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 = {selected}, 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 }

Projects

BibSonomy (news, Twitter, source code: Bitbucket)
A social bookmark and publication sharing system with lots of cool features!
PUMA
DZ.PTM
Digitalisierungszentrum Präzisions- und Telemedizin

Teaching

Seminar Ausgewählte Themen des Web 2.0 (winter term 2016/17, 2014/15, 2013/14 summer term 2014)
Data Mining (summer term 2018, 2017, 2016, 2015, 2014)
Open Thesis / Practica