Category: News
-
RecSys Workshop 2024: Exploring AI Collaboration🤝
The RecSys Workshop held at TU Wien on September 9th and 10th, 2024, brought together leading minds in the field of recommender systems to explore the evolving collaboration between humans and AI. Organized by the Christian Doppler Lab for Recommender Systems, this event aimed to delve into the complexities and opportunities of AI-human collaboration in…
-
Presentation @ UMAP ’24
I’m (Thomas Kolb) happy to share that I presented two of our research papers from the Christian Doppler Lab for Recommender Systems at the workshops of ACM UMAP 2024! 🎉 Evaluating Group Fairness in News Recommendations: A Comparative Study of Algorithms and Metrics (Blake Huebner, Thomas Kolb, Julia Neidhardt)Link: https://dl.acm.org/doi/10.1145/3631700.3664897 Classifying User Roles in Online…
-
Publication at LREC-COLING 2024
Our lab proudly announces the publication of “PopAut: An Annotated Corpus for Populism Detection in Austrian News User Comments.” Authored by Ahmadou Wagne, with support from Julia Neidhardt and Thomas Kolb, this work provides the first German-language corpus annotated for populist motives.The research, presented as a poster at the joint LREC-COLING conference in Torino, Italy, sparked engaging discussions and…
-
Hands-on Session AI @ AK-Tag
It was a pleasure for me to conduct a hands-on session on the possibilities, limitations, and challenges of AI at the AK-Tag 2024 [1] of the Federal Bureau of Anti-Corruption (BAK)! This showcase was created in collaboration with my colleague Ahmadou Wagne as part of our research in the Christian Doppler Laboratory for Recommender Systems.…
-
Unlocking the Potential of Content-Based Restaurant Recommender Systems: Insights from ENTER Conference 2024
Today, Thomas E. Kolb, had the pleasure of presenting our work, “Unlocking the Potential of Content-Based Restaurant Recommender Systems” at the ENTER Konferenze 2024, in Izmir, Turkey. đź“š Our research focuses on optimizing dining experiences by examining the effectiveness of TF-IDF and SBERT models. This study not only assesses these models on a technical level…