The AI for Society Lab is a research group in the Department of Computer Science and Biomedical Engineering at the Institute of Interactive Systems and Data Science at Graz University of Technology, Austria. We are committed to producing high-quality, responsible and reproducible research results.
Research examples include novel approaches for recommender systems, user modeling, information retrieval, machine learning, trustworthy AI, and computational social science, with a particular focus on psychological models for recommender systems [1], session-based recommender systems [2], privacy in recommender systems [3], detecting and mitigating bias in recommendation algorithms [4], music recommender system, specifically modeling of non-mainstream music consumption [5], robustness issues of GNNs [6], and NLP-based studies of polarization in social media [7,8].
Selected References:
[1] Lex, E., Kowald, D., Seitlinger, P., Tran, T. N. T., Felfernig, A., & Schedl, M. (2021). Psychology-informed Recommender Systems. Foundations and Trends® in Information Retrieval, 15(2), 134-242
[2] Lacic, E., Reiter-Haas, M., Kowald, D., Reddy Dareddy, M., Cho, J., & Lex, E. (2020). Using autoencoders for session-based job recommendations. User Modeling and User-Adapted Interaction, 30(4), 617-658.
[3] Muellner, P., Kowald, D., & Lex, E. (2021). Robustness of Meta Matrix Factorization Against Strict Privacy Constraints. In European Conference on Information Retrieval (pp. 107-119). Springer, Cham.
[7] Kowald, D., Schedl, M., & Lex, E. (2020). The unfairness of popularity bias in music recommendation: A reproducibility study. In European Conference on Information Retrieval (pp. 35-42). Springer, Cham
[5] Kowald, D., Muellner, P., Zangerle, E., Bauer, C., Schedl, M., & Lex, E. (2021). Support the underground: characteristics of beyond-mainstream music listeners. EPJ Data Science, 10(1), 14.
[6] Hussain, H., Duricic, T., Lex, E., Helic, D., Strohmaier, M., & Kern, R. (2021). Structack: Structure-based Adversarial Attacks on Graph Neural Networks. In Proceedings of the 32nd ACM Conference on Hypertext and Social Media (pp. 111-120).
[7] Reiter-Haas, M., Kopeinik, S., Lex, E. (2021). Studying Moral-based Differences in the Framing of Political Tweets. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 15, pp. 1085-1089).
[8] Reiter-Haas, M., Kloesch, B., Hadler, M., Lex, E. (2022). Polarization of opinions on covid-19 measures: Integrating twitter and survey data. Social Science Computer Review (to appear), 2022.
Recent/Upcoming Tutorials
- UMAP 2024: Trustworthy User Modeling and Recommendation From Technical and Regulatory Perspectives
- WSDM 2023: Trustworthy Algorithmic Ranking Systems
- WEBCONF 2022: PIRS - Psychology-informed Recommender Systems
- SIGIR 2022: Retrieval and Recommendation Systems at the Crossroads of Artificial Intelligence, Ethics, and Regulation
- RecSys 2022: PIRS - Psychology-informed Recommender Systems
Current Projects
Selected GitHub Repositories:
- Predicting Music Relistening Behavior Using the ACT-R Framework
- Studying Moral-based Differences in the Framing of Political Tweets
- Robustness of Meta Matrix Factorization Against Decreasing Privacy Budgets
- Support the Underground: Characteristics of Beyond-Mainstream Music Listeners
- The Unfairness of Popularity Bias in Music Recommendation: A Reproducibility Study
Team
Head: Assoc. Prof. Dr. Elisabeth Lex
PhD students:
- Peter Muellner
- Tomislav Duricic
- Kevin Innerebner
- Master’s students:
- Julian Kainz
- Gregor Mayr
- Christoph Schatz
- Stefan Russmann
Bachelor’s students:
- Jakob Zenz
- Christian Falk-Ohrenhofer
- Manuel Riedl
- Nico Ohler
- Adam Urosevic
Alumni:
- Markus Reiter-Haas
- Emanuel Lacic
- Dominik Kowald
- Ilire Hasani-Mavriqi
- Simone Kopeinik
- Julian Rudolf
- Alexander Ertl
- Irene Strauss
- Lukas Preitler
- Sandra Haas
- Edina Mulahasanovic
- Daniel Scharf
Teaching
- Advanced Information Retrieval/Web Technology
Project Highlights: WS 2022, WS 2023 - Introduction to Computational Social Systems
- Recommender Systems
- Human Rights and Artificial Intelligence
- Legal Lab 1
- Legal Lab 2
- Introduction to Structured Programming (Lecture and Design practical)
- Introduction to Scientific Working
Contact
Social media: @socialcomplab
TU Graz: ISDS