News - Data Science Chair

Studying in Würzburg - between vineyards, fortress and residence? You can choose from about 250 subjects. If this has sparked your interest, this video will give you a little insight into the possibilities and student life in Würzburg.

Our short paper "Where to Submit? Helping Researchers to Choose the Right Venue" was accepted for publication in Findings of EMNLP.

Together with researchers from Leipzig University and Bauhaus University Weimar, we organized this year's ECML-PKDD discovery challenge called "ChAT", which is an acronym for "Chat Analytics for Twitch".

Abgeordnete des bayrischen Landtags besuchten die Universität Würzburg zum Austausch über das BigData@Geo Projekt.

An der Uni Würzburg entsteht ein Center for Artificial Intelligence in Data Science (CAIDAS). Über dessen Forschung hat sich nun Staatsministerin Dorothee Bär vor Ort informiert.

Bei einer Online-Podiumsdiskussion sprechen Fachleute aus Wissenschaft, Medien und Politik über Fake News in Zeiten von Corona. Zuhörer sind willkommen; die Diskussion startet am Donnerstag, 30. Juli, um 15 Uhr.

Our paper "Integrating Keywords into BERT4Rec for Sequential Recommendation" (KeBERT4Rec) was recently accepted at the KI2020 conference. In our approach, we enrich the BERT4Rec architecture used for sequential recommendation with keywords as a way to incorporate information about the items. Our paper will be presented at the KI2020 and published in the proceedings.

Our paper “SimLoss: Class Similarities in Cross Entropy” was accepted for publication at ISMIS 2020.

Our paper "Improving Sentiment Analysis with Biofeedback Data" was recently published.

In this cooperative work between the Data Science chair and the chair of Human-Computer-Interaction, we present an approach of incorporating biofeedback features derived from heart rate and brain waves signals. The biofeedback data was recorded from “Humans-in-the-Loop” to improve machine learning models on the tasks of sentiment analysis and sentiment detection.

In our paper "OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning" that was recently published at atmospheric environment we introduced OpenLUR, an easily and globally applicable land use regression framework for air pollution modelling.