News Recommendation Workshop at ACM RecSyS 2025

News Recommendation Workshop at ACM RecSyS 2025

International cooperation for our Recommender System Workshop at RecSyS

By end of September 2025, the ACM RecSys 2025 conference was held in Prague, Czech Republic. The NorwAI team, consisting Associate Professor Özlem Özgöbek, Associate Professor Benjamin Kille and PhD student Vandana Yadav collaborated with international partners for organizing the 13th International Workshop on News Recommendation and Analytics (INRA 2025) this year. The Departement of Computer Science at NTNU has contributed to this conference for a number of years.

The ACM RecSyS is an A-ranked  peer-reviewed academic conference series about recommender systems which focuses on issues such as algorithms, machine learning, human-computer interaction and data science in a multi-disciplinary perspective. It is held annually in different locations globally on all continents. The conference brings together academics and industry experts to present new research results, systems and techniques within recommender systems. INRA workshop series has been hosted by the ACM RecSys Conference for a number of years. 

-    We invited Dr. Marcel Hauck as key note speaker in our workshop. He is a technical project manager at the German public service media organization ARD, where he works on the development, deployment and evaluation of recommender systems, says Özlem Özgöbek on behalf of the team.  

The abstract

His presentation was «Public Service Media Recommender Systems – Engagement, Public Value, and Efficiency in the Wild».  According to the abstract, public service media (PSM) face the dual challenge of meeting societal mandates while ensuring platform effectiveness. The talk presented  empirical findings from an A/B test on ARD Mediathek’s Video-on-Demand recommender system. 

The results demonstrated that less complex models can match or exceed advanced approaches in user engagement, public value metrics, and operational efficiency, including cost and carbon footprint. 

The analysis addressed observed discrepancies between offline and online evaluations and discusses practical challenges for PSM recommender systems. To support further research, a real-world dataset from the study is available to the scientific community.

In addition to the keynote speech by Dr. Marcel Hauck, the workshop has accepted a 10 peer-reviewed papers for presentation. The workshop had a focus on topics covering news personalization, news analytics, societal, legal, and ethical aspects of news personalization systems, and the effects of generative AI on the news ecosystem, welcoming both technical contributions and interdisciplinary work.

-    The workshop had five long and five flash presentations, and all the presenters also had posters. About 50 attendees followed the workshop, says Özlem Özgöbek. 

A growing community

The INRA workshop series was initiated 13 years ago at the RecSys Conference by now the members of NorwAI. Since then, NorwAI and the Department of Computer Science at NTNU contributed to this conference for a number of years. In addition, to ACM RecSys, INRA workshop series was organized in other conferences such as CIKM and UMAP in the previous years. 

- The attendance and interest in the workshop has been growing especially in the last couple of years. We see more people from various national and international news media organizations, tech companies working with news recommender systems and scholars from all around the world, says Özlem Özgöbek.

News Recommendation Workshop at ACM RecSyS 2025

  • Dr Marcel Hauck at at the German public service media organisation ARD presented a key note on the dual challenge of meeting societal mandates while ensuring platform effectiveness.

News Recommendation Workshop at ACM RecSyS 2025

  • The representatives from Recombee, a AI-powered recommendation platform, presented a strategic partnership with UK news organization The Telegraph to power personalised content recommendations across its website and app.

News Recommendation Workshop at ACM RecSyS 2025

2025-10-30

By Rolf D. Svendsen 
Source on ACM RecSyS: Wikipedia