Team

Recommender Systems
Beyond Accuracy Measurements
Generative AI
News Recommendations
Thomas E. Kolb
Predoc Researcher
I am a predoctoral researcher at TU Wien, focusing on recommender systems, generative AI, and the responsible use of machine learning in digital media environments. My research explores topics such as fairness and bias in news recommendations, cross-domain recommendation approaches, and beyond-accuracy evaluation methods. Recently, I have extended my work towards generative AI, investigating its integration into retrieval-augmented generation systems and human-centered applications. I am actively involved in teaching and mentoring, having supervised numerous master’s and bachelor’s theses in areas like sentiment analysis, fairness in recommendations, and content-based recommender systems. In addition to research and teaching, I contribute to the community by organizing scientific events and workshops, reviewing for international journals, and taking on various voluntary roles — including serving as IT representative for the Students’ Union at TU Wien, as well as being an active member of the Association for Digital Humanism.
Teaching
- 194.035 Recommender Systems 2021, 2022, 2023, 2024, 2025
- 194.050 Social Network Analysis 2021, 2022, 2024
- 194.164 Advanced Topics in Recommender Systems and Generative AI 2024, 2025
Activities & Talks
- Organizer at the ACM Summer School on Recommender Systems 2025
- Co-Chair of the LLM4Good Workshop co-located with ACM UMAP 2025
- Speaker at the Parliamentary Administration: “Generative AI in legislative consultation procedures”
- Speaker at “Lehrende helfen Lehrenden” at TU Wien for our lecture “Social Network Analysis”
- Speaker at MediaWiki Users and Developers Conference Fall 2024
- Speaker at ÖVG Herbsttagung 2024
- Organizer at the 3rd ACM Digital Humanism Summer School
- Speaker at AK-Tag 2024 (Anti-Corruption Day of the Federal Bureau of Anti-Corruption)
- Guest Lecture Session at FH Krems (Topic: Recommender Systems): 2024, 2025
- Organizer & Speaker at 2nd ACM Digital Humanism Summer School: Hands-On Session Chat-GPT
- Speaker at ÖAW AI Winter School 2023: Sentiment Analysis
- Participant at RecSys Summer School 2023
- Student Volunteer at the 16th ACM Conference on Recommender Systems
- Speaker at Workshop: Österreichisches Treffen zu Sentimentinferenz (ÖTSI) Österreichische Linguistik-Tagung 2021: Sentiment Analysis
Supervisions
Master Theses
- COVID-19 and Populism in Austrian News User Comments – A Machine Learning Approach / Wagne, A. (2023). COVID-19 and Populism in Austrian News User Comments – A Machine Learning Approach [Diploma Thesis, Technische Universität Wien]. reposiTUm. (completed)
https://doi.org/10.34726/hss.2023.105940 - Exploring Group Fairness in News Media Recommendations: Algorithms, Metrics, and Grouping / Huebner, B. (2023). Exploring Group Fairness in News Media Recommendations: Algorithms, Metrics, and Grouping [Diploma Thesis, Technische Universität Wien]. reposiTUm. (completed)
https://doi.org/10.34726/hss.2023.107255 - Steindl, B. (2024). Evaluating the fairness of news recommender algorithms within detected user communities [Diploma Thesis, Technische Universität Wien]. reposiTUm. (completed)
https://doi.org/10.34726/hss.2024.115142 - Hofmaier, M. (2024). Exploration of content-based cross-domain podcast recommender systems [Diploma Thesis, Technische Universität Wien]. reposiTUm. (completed)
https://doi.org/10.34726/hss.2024.112170 - Analysing Dynamics Over Time of Bias in Recommender Systems, Boris Staykov (in progress)
- POI Recommender Systems for Customized Walking Tours Using Context and Category, Joanna Zamiechowska (in progress)
- Intent Discovery and Product Search for Price Comparison Sites, Dante Godolja (in progress)
- Named Entity Recognition for District Identification in Digital Journalism: A Study in News and Lifestyle Media, Singh Manpreet (in progress)
- Designing and Evaluating a Human-Centered Retrieval-Augmented Generation System Using Heterogeneous Data, Naceva Dragana (in progress)
Bachelor Theses
- Stimmungsanalyse von geclusterten COVID-19 Artikel zum Thema Maskenpflicht: Ein Vergleich mit User-Kommentaren / Burtscher, L. (2023) (completed)
- Content-Based Restaurant Recommendation Systems Using Textual and Visual Data / Godolja, D. (2023) (completed)
- K-Means Clustering of Fashion Behavior: A Language-Focused Approach / Dedov, F. (2022) (completed)
- Evaluating Local Hosting Solutions for Large Language Models: A Cost-Centric Analysis of Performance, Compliance, and Scalability / Eichler, L. (in progress)
- Spread of Missinformation / Weich, M. (in progress)
Voluntary Engagement
- Reviewer for ACM Transactions on Recommender Systems (TORS), Information Technology & Tourism (JITT) and KONVENS
- Senate at TU Wien
- Since 11/2024: Member of the Association to support Digital Humanism
- Since 05/2022: Student Advisor (Representation of Interests of Doctoral Candidates at TU Wien)
- Study commission for doctoral students
- Since 03/2020: System Administrator/Architect (Students’ Union at the TU Wien – Department for Digitalization and Infrastructure)
- Since 07/2010: (Voluntary) Firefighter (IT-Representative)
Publications
2024
PopAut: An Annotated Corpus for Populism Detection in Austrian News Comments Proceedings Article
In: Calzolari, Nicoletta; Kan, Min-Yen; Hoste, Veronique; Lenci, Alessandro; Sakti, Sakriani; Xue, Nianwen (Ed.): Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 12879–12892, ELRA and ICCL, Torino, Italy, 2024.
Unlocking the Potential of Content-Based Restaurant Recommender Systems Proceedings Article
In: Berezina, Katerina; Nixon, Lyndon; Tuomi, Aarni (Ed.): Information and Communication Technologies in Tourism 2024, pp. 239–244, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-58839-6.
Classifying User Roles in Online News Forums: A Model for User Interaction and Behavior Analysis Proceedings Article
In: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, pp. 240–249, Association for Computing Machinery, Cagliari, Italy, 2024, ISBN: 9798400704666.
Navigating Serendipity – An Experimental User Study On The Interplay of Trust and Serendipity In Recommender Systems Proceedings Article
In: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, pp. 386–393, Association for Computing Machinery, Cagliari, Italy, 2024, ISBN: 9798400704666.
Evaluating Group Fairness in News Recommendations: A Comparative Study of Algorithms and Metrics Proceedings Article
In: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, pp. 337–346, Association for Computing Machinery, Cagliari, Italy, 2024, ISBN: 9798400704666.
Enhancing Cross-Domain Recommender Systems with LLMs: Evaluating Bias and Beyond-Accuracy Measures Proceedings Article
In: Proceedings of the 18th ACM Conference on Recommender Systems, pp. 1388–1394, Association for Computing Machinery, Bari, Italy, 2024, ISBN: 9798400705052.
2023
Like a Skilled DJ – an Expert Study on News Recommendations Beyond Accuracy Proceedings Article
In: Kille, Benjamin (Ed.): CEUR-WS.org, 2023.
Potentials of Combining Local Knowledge and LLMs for Recommender Systems Proceedings Article
In: Anelli, Vito Walter; Basile, Pierpaolo; Melo, Gerard De; Donini, Francesco; Ferrara, Antonio; Musto, Cataldo; Narducci, Fedelucio; Ragone, Azzurra; Zanker, Markus (Ed.): pp. 61–64, CEUR-WS.org, 2023.
2022
The ALPIN Sentiment Dictionary: Austrian Language Polarity in Newspapers Proceedings Article
In: pp. 4708–4716, European Language Resources Association, Marseille, France, 2022.
The Role of Bias in News Recommendation in the Perception of the Covid-19 Pandemic Proceedings Article
In: Thomas, Kolb (Ed.): 2022.
Dynamic sentiment analysis for measuring media bias Masters Thesis
Technische Universität Wien, Wien, 2022.
2021
A review and cluster analysis of German polarity resources for sentiment analysis Proceedings Article
In: 3rd Conference on Language, Data and Knowledge (LDK 2021), pp. 1–17, OASICS, 93, 2021, ISBN: 978-3-95977-199-3.
Creating an Austrian language polarity dictionary with the crowd Miscellaneous
2021.