Paper-Conference

Designing Trustworthy LLM-based Wellbeing Recommendation through Controllable Interaction
Large language models (LLMs) are increasingly used to generate personalized guidance in wellbeing contexts such as physical activity, …
Alan Said, Alexandra Weilenmann
Cite paper
Designing Trustworthy LLM-based Wellbeing Recommendation through Controllable Interaction
Trust as a Situated User State in Social LLM-Based Chatbots: A Longitudinal Study of Snapchat’s My AI
Social chatbots based on large language models are increasingly embedded in everyday platforms, yet how users develop trust in these …
Annie Landerberg, Kari Flatmo, Alan Said
Cite paper
Trust as a Situated User State in Social LLM-Based Chatbots: A Longitudinal Study of Snapchat’s My AI
When Personalization Conflicts with Sustainability: A System-Level Perspective
Personalized systems increasingly shape what people consume, watch, learn, and purchase at global scale, yet they are typically …
Alan Said
Cite preprint
When Personalization Conflicts with Sustainability: A System-Level Perspective
Early Explorations of Recommender Systems for Physical Activity and Well-being
As recommender systems increasingly guide physical actions, often through wearables and coaching tools, new challenges arise around how …
Alan Said
Cite preprint
Early Explorations of Recommender Systems for Physical Activity and Well-being
On the Reliability of Sampling Strategies in Offline Recommender Evaluation
Offline evaluation plays a central role in benchmarking recommender systems when online testing is impractical or risky. However, it is …
Bruno L Pereira, Alan Said, Rodrygo Santos
Cite preprint ACM DOI
On the Reliability of Sampling Strategies in Offline Recommender Evaluation
The Hidden Cost of Defaults in Recommender System Evaluation
Hyperparameter optimization is critical for improving the performance of recommender systems, yet its implementation is often treated …
Hannah Berling, Robin Svahn, Alan Said
Cite preprint ACM DOI
The Hidden Cost of Defaults in Recommender System Evaluation
We're Still Doing It (All) Wrong: Recommender Systems, Fifteen Years Later
In 2011, Xavier Amatriain sounded the alarm: recommender systems research was ‘doing it all wrong’ [1]. His critique, …
Alan Said, Maria Soledad Pera, Michael D. Ekstrand
Cite preprint
We're Still Doing It (All) Wrong: Recommender Systems, Fifteen Years Later
Soundtracks of Our Lives: How Age Influences Musical Preferences
The majority of research in recommender systems, be it algorithmic improvements, context-awareness, explainability, or other areas, …
Arsen Matej Golubovikj, Bruce Ferwerda, Alan Said, Marko Tkalcic
Cite preprint
Soundtracks of Our Lives: How Age Influences Musical Preferences
Tell Me the Good Stuff: User Preferences in Movie Recommendation Explanations
Recommender systems play a vital role in helping users discover content in streaming services, but their effectiveness depends on users …
Juan Ahmad, Jonas Hellgren, Alan Said
Cite preprint
Tell Me the Good Stuff: User Preferences in Movie Recommendation Explanations
Checky, the Paper-Submission Checklist Generator for Authors, Reviewers and LLMs
Submission checklists have become increasingly prevalent for paper submissions to conferences and journals in machine learning …
Joeran Beel, Bela Gipp, Dietmar Jannach, Alan Said, Lukas Wegmeth, Tobias Vente
Cite Springer DOI
Checky, the Paper-Submission Checklist Generator for Authors, Reviewers and LLMs