Vnímání férovosti ve skupinových doporučovacích systémech

• Thesis title in Czech: Vnímání férovosti ve skupinových doporučovacích systémech
• Thesis title in English: Perception of fairness in group recommender systems
• Academic year of topic announcement: 2024/2025
• Thesis type: Bachelor's thesis
• Department: Department of Software Engineering (32-KSI)
• Supervisor: RNDr. Patrik Dokoupil

Guidelines

This topic is concerned with studying users' perception of fairness in group recommender systems (GRS). The student should first gain basic knowledge about recommender systems (RS), GRS, and fairness in the context of RS (see literature). After that, the student should check approaches for studying fairness used in related work.

The main aim of this thesis is to prepare and evaluate a user study focusing on how people perceive fairness in group recommender systems. The student should also focus on whether and how the fairness perception of individuals changes based on when the individual is or is not a member of the group itself. The supposed domain is the movie domain but can be adjusted according to student's preferences.

References

1. Ricci, F. et al (Eds): Recommender Systems Handbook, Springer, 2022

2. Felfernig, A. \& Boratto, L. \& Stettinger, M. \& Tkalčič, M. (2018). Group Recommender Systems - An Introduction.

3. Mesut Kaya, Derek Bridge, Nava Tintarev: Ensuring Fairness in Group Recommendations by Rank-Sensitive Balancing of Relevance, https://dl.acm.org/doi/10.1145/3383313.3412232

4. Dimitris Serbos, Shuyao Qi, Nikos Mamoulis, Evaggelia Pitoura, and Panayiotis Tsaparas. 2017. Fairness in Package-to-Group Recommendations. In Proceedings of the 26th International Conference on World Wide Web (WWW '17). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE, 371–379.

5. Dimitris Sacharidis. 2019. Top-N group recommendations with fairness. In Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing (SAC '19). Association for Computing Machinery, New York, NY, USA, 1663–1670.

6. Ladislav Malecek and Ladislav Peska. 2021. Fairness-preserving Group Recommendations With User Weighting. In Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization (UMAP '21). Association for Computing Machinery, New York, NY, USA, 4–9.

7. Lin Xiao, Zhang Min, Zhang Yongfeng, Gu Zhaoquan, Liu Yiqun, and Ma Shaoping. 2017. Fairness-Aware Group Recommendation with Pareto-Efficiency. In Proceedings of the Eleventh ACM Conference on Recommender Systems (RecSys '17). Association for Computing Machinery, New York, NY, USA, 107–115.

Preliminary scope of work in English

Recommender systems are tools that are ubiquitous in our everyday lives and their importance is still growing. Nowadays, most online services, for example, social networks, news services, streaming services, or news websites adopt some form of a recommendation. Since people are exposed to recommender systems on a daily basis and they are affected by their performance, fairness, and other attributes, it should be our role (as researchers) to work on improving these systems and preventing possible negative effects they may pose to the user. One of the emerging sub-domains of recommender systems is group recommender systems, where the goal is to recommend items to whole groups of people, instead of individuals, for example, recommend a movie to a group of friends to watch together. Despite the fact that group recommender systems are becoming more and more popular (and thus studied) they are still not understood well enough. Some of the questions that still don't have a clear answer are those related to fairness, e.g. how do people perceive fairness of group recommender system? What do they consider to be fair? Does all of that change if they are or are not part of the group? And so on. The main goal of this thesis is to help answer some of these questions.

This topic lies on a border between "implementation based thesis" (implementing the user study plugin/website) and "research based thesis" (conducting and evaluating the user stud). We expect that thesis results will be published at some international conference (co-authored by the student).