2nd Semester 2025/26: User Perception of Recommender Systems on Social Media

Instructors

Matteo Fabbri

Description

Social media platforms use recommender systems to reduce information overload and enhance user experience but do not usually address the implications of their influence on users from an ethical and legal perspective. The Digital Services Act (DSA) is the first supranational regulation that requires online platforms to explain the criteria underlying their recommender systems and to allow users to control them by modifying their parameters. However, the effectiveness of user control features is mainly dependent on the design of the interface: in fact, users may not be interested in using tools that, despite supporting their empowerment, may increase the cognitive load of their experience. Through optimizing a pre-developed platform simulation based on YouTube Shorts, students will design algorithmic metrics for meaningful personalization and user empowerment to answer the following question: how can users be motivated to engage with control options to intervene on how recommender systems influence them?

This project is methodologically flexible, involving different approaches depending on the expertise of the students. Possible subjects involve: experimental philosophy, moral psychology, human-computer interaction, game theory, legal design.

Organisation

Interested students will meet with the instructor on the first week of June to agree on the type of contribution they are expected to make based on their background and interests. The instructor will introduce the topic and indicate possible avenues for a joint research project.

Prerequisites

Essential: Good programming skills (in Python or other programming languages depending on research method); Interest in AI ethics, platform governance, and social influence of recommender systems.

Preferred: Experience with software development; Acquaintance with European digital laws.

Assessment

Joint research project to be assessed through student presentations, potentially leading to a publication depending on quality of the output.

References

Fabbri, M., & Boratto, L. (2025). Auditing Recommender Systems for User Empowerment in Very Large Online Platforms under the Digital Services Act. In Proceedings of the Nineteenth ACM Conference on Recommender Systems (pp. 51-61). https://doi.org/10.1145/3705328.3748074

 

Hakkarainen, J., & Savolainen, L. (2025). Individual choice, collective effects: recommender systems, law by design, and the DSA’s double choice architecture. Information, Communication & Society, 1-18. https://doi.org/10.1080/1369118X.2025.2595663

 

Pope, N., Kahila, J., Laru, J., Vartiainen, H., Roos, T., & Tedre, M. (2024). An educational tool for learning about social media tracking, profiling, and recommendation. 2024 IEEE International Conference on Advanced Learning Technologies (ICALT), 110–112. https://doi.org/10.1109/ICALT61570.2024.00038 

 

Starke, C., Metikoš, L., Helberger, N., & de Vreese, C. (2025). Contesting personalized recommender systems: a cross-country analysis of user preferences. Information, Communication & Society, 28(1), 41-60. https://doi.org/10.1080/1369118X.2024.2363926