mendation and Analytics (INRA 2025)

Abstract

Recommender systems play a central role in today's digital news ecosystem, helping users navigate the overwhelming volume of information with personalized and context-aware suggestions. Ensuring trustworthy, fair, and diverse recommendations, while addressing issues such as misinformation, filter bubbles, privacy, and ethics, remains a pressing concern. The 13th edition of the INRA workshop gathers researchers, practitioners, and stakeholders to explore these technical, societal, and ethical dimensions of news recommendation.

Keywords

• The news ecosystem has undergone significant transformations during the past decade
• Faced with an

2. Accepted Contributions

The call for participation motivated researchers to submit their findings in the form of regular or short papers, including demo and idea papers. Seventeen submissions were received. A thorough peer-review allowed to accept 10 submissions for presentation at the workshop, including 5 regular papers and 5 short papers (3 short papers, 2 demo papers, 1 idea paper).

1. More of the Same? A Longitudinal Evaluation of Two Similarity-based Approaches in a News 2. News, With a Twist: Using Contrastive Learning to Improve User Embeddings for Diverse News

CEUR

ceur-ws.org

3. Program Committee

We recruited a set of experts to assure the quality of the accepted papers. We would like to thank: • Geofray Bonnin, Université de Lorraine - LORIA • Tanise Ceron, University of Stuttgart • Goran Glavaš, CAIDAS - University of Würzburg • Lucien Heitz, University of Zurich • Mesut Kaya, IT University Copenhagen • Anton Korlkov, University of Toronto • Chahrazed Labba, Université de Lorraine - LORIA • Edward Malthouse, Northwestern University • Lucas Moeller, University of Stuttgart • Heiko Paulheim, University of Mannheim • Fabian Schmidt, University of Würzburg • Alain D. Starke, Universiteit van Amsterdam • Hanne Vandenbroucke, imec-SMIT Vrije Universiteit Brussel • Sanne Vrijenhoek, Universiteit van Amsterdam • Andreea Iana, University of Mannheim • Célina Treuillier, Human-IST Institute, University of Fribourg • Vandana Yadav, Norwegian University of Science and Technology • Benjamin Kille, Norwegian University of Science and Technology • Andreas Lommatzsch, TU Berlin • Özlem Özgöbek, Norwegian University of Science and Technology

References

3. Leveraging Media Frames to Improve Normative Diversity in News Recommendations by Sourabh Dattawad, Agnese Dafara , and Tanise Ceron

4. Using Large Language Models to 'Lighten the Mood': Satirically Reframing News Recommendations to Reduce News Avoidance by Tobias Jovall Wessel , Christoph Trattner, and Alain D. Starke

5. Hope , Fear, or Anger? How Emotional Framing in a News Recommender System Guides User Preferences by Jørgen Eknes-Riple, Jia-Hua Jeng , Alain D. Starke , Khadiga Seddik, and Christoph Trattner

6. Segment-Aware Analytics for Real-Time Editorial Support in Media Groups by Martin Spišák , Rodrigo Alves, Thomas Kelleher, Jason Sheppard, Ondřej Fiedler, Ergys Kosovrasti, Vojtěch Vančura, Petr Kasalický, and Pavel Kordík

7. News Recommendation with Category Description by a Large Language Model by Yuki Yada and Hayato Yaman

8. Clickbait mitigation in industrial recommender system by Václav Blahut, Karel Koupil , Michal Chudoba, and Radek Tomšů

9. Evaluating Image Trust Labels in a News Recommender System by Svenja Lys Forstner , Yelyzaveta Lysova, Alain Starke, and Christoph Trattner

10. Towards Multi-Aspect Diversification of News Recommendations Using Neuro-Symbolic AI for Individual and Societal Benefit by Markus Reiter-Haas and Elisabeth Lex