Popularity bias in recommender systems

Ivan Demianov, Dmitry Namiot

Abstract


Recommender systems play a crucial role in modern digital platforms by providing personalized recommendations that enhance user experience. Today, recommendations are successfully integrated into marketplaces, movie streaming services, and music platforms. The primary goal of a recommender system is to predict the most relevant items for each user. Typically, this task is solved using machine learning methods that take into account user data, platform items, and user-item interaction matrices. However, such an approach often leads to the problem of popularity bias, where recommendation algorithms excessively favor popular items. This paper aims to review the metrics for detecting popularity bias in recommender systems. Additionally, it provides an overview of strategies designed to mitigate popularity bias, discussing their advantages and disadvantages.

Full Text:

PDF (Russian)

References


Almazro, Dhoha, et al. «A survey paper on reccommender systems.» arXiv preprint arXiv:1006.5278 (2010).

Mukherjee, Subhabrata, Hemank Lamba, and Gerchard Weikum. «Item recommendation with evolving user preferences and experience.» arXiv preprint arXiv:1705.02519 (2017).

Roy, Deepjyoti, and Mala Dutta. «A systematic review and research perspective on recommender systems.» Journal of Big Data 9.1 (2022): 59.

Sankalp, K. J., et al. «Advancements in Modern Recommender Systems: Industrial Applications in Social Media, E-commerce, Entertainment, and Beyond.» (2024).

Górski, Franciszek, et al. «Integrating Expert Knowledge into Logical Programs via LLMs.» arXiv preprint arXiv:2502.12275 (2025).

Aggarwal, Charu C., and Charu C. Aggarwal. «Content-based recommender systems.» Recommender systems: The textbook (2016): 139-166.

Ekstrand, Michael D., John T. Riedl, and Joseph A. Konstan. «Collaborative filtering recommender systems.» Foundations and Trends® in Human–Computer Interaction 4.2 (2011): 81-173.

Burke, Robin. «Hybrid recommender systems: Survey and experiments.» User modeling and user-adapted interaction 12 (2002): 331-370.

Wang, Shoujin, et al. «A survey on session-based recommender systems.» ACM Computing Surveys (CSUR) 54.7 (2021): 1-38.

Anelli, Vito Walter, et al. «On the discriminative power of hyper-parameters in cross-validation and how to choose them.» Proceedings of the 13th ACM conference on recommender systems. 2019.

Luo, Xin, et al. «An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems.» IEEE Transactions on Industrial informatics 10.2 (2014): 1273-1284.

Gangwar, Ajay, and Shweta Jain. «An adaptive boosting technique to mitigate popularity bias in recommender system.» arXiv preprint arXiv:2109.05677 (2021).

Klenitskiy, Anton, and Alexey Vasilev. «Turning dross into gold loss: is bert4rec really better than sasrec?.» Proceedings of the 17th ACM Conference on Recommender Systems. 2023.

Abdollahpouri, Himan, Robin Burke, and Bamshad Mobasher. «Managing popularity bias in recommender systems with personalized re-ranking.» arXiv preprint arXiv:1901.07555 (2019).

Abdollahpouri, Himan, et al. «User-centered evaluation of popularity bias in recommender systems.» Proceedings of the 29th ACM conference on user modeling, adaptation and personalization. 2021.

Klimashevskaia, Anastasiia, Mehdi Elahi, and Christoph Trattner. «Addressing popularity bias in recommender systems: An exploration of self-supervised learning models.» Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization. 2023.

Mansoury, M., et al. «FairMatch: A graph-based approach for improving aggregate diversity in recommender systems. arXiv 2020.» arXiv preprint arXiv:2005.01148 (2005).

Hurley, Neil, and Mi Zhang. «Novelty and diversity in top-n recommendation–analysis and evaluation.» ACM Transactions on Internet Technology (TOIT) 10.4 (2011): 1-30.

Li, Roger Zhe, Julián Urbano, and Alan Hanjalic. «Leave no user behind: Towards improving the utility of recommender systems for non-mainstream users.» Proceedings of the 14th ACM International Conference on Web Search and Data Mining. 2021.

Jadidinejad, Amir H., Craig Macdonald, and Iadh Ounis. «Unifying explicit and implicit feedback for rating prediction and ranking recommendation tasks.» Proceedings of the 2019 ACM SIGIR international conference on theory of information retrieval. 2019.

Park, Yoon-Joo, and Alexander Tuzhilin. «The long tail of recommender systems and how to leverage it.» Proceedings of the 2008 ACM conference on Recommender systems. 2008.

Kamishima, Toshihiro, et al. «Correcting popularity bias by enhancing recommendation neutrality.» RecSys posters 10 (2014).

Wang, Xiuling, and Wendy Hui Wang. «Providing item-side individual fairness for deep recommender systems.» Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency. 2022.

Steck, Harald. «Item popularity and recommendation accuracy.» Proceedings of the fifth ACM conference on Recommender systems. 2011.

Zhu, Ziwei, et al. «Popularity bias in dynamic recommendation.» Proceedings of the 27th ACM SIGKDD conference on knowledge discovery data mining. 2021.

Schnabel, Tobias, et al. «Recommendations as treatments: Debiasing learning and evaluation.» international conference on machine learning. PMLR, 2016.

Kang, Wang-Cheng, and Julian McAuley. «Self-attentive sequential recommendation.» 2018 IEEE international conference on data mining (ICDM). IEEE, 2018.

Ninichuk, Marina, and Dmitry Namiot. «Survey On Methods For Building Session-Based Recommender Systems.» International Journal of Open Information Technologies 11.5 (2023): 22-32.

Prakash, Arushi, Dimitrios Bermperidis, and Srivas Chennu. «Evaluating Performance and Bias of Negative Sampling in Large-Scale Sequential Recommendation Models.» arXiv preprint arXiv:2410.17276 (2024).

Gao, Chongming, et al. «SPRec: Leveraging SelfPlay to Debias Preference Alignment for Large Language Model-based Recommendations.» arXiv preprint arXiv:2412.09243 (2024).

Carbonell, Jaime, and Jade Goldstein. «The use of MMR, diversity-based reranking for reordering documents and producing summaries.» Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval. 1998.

Thangaraj, Harish, et al. «A BERT Based Hybrid Recommendation System For Academic Collaboration.» arXiv preprint arXiv:2502.15223 (2025).

Sani, S. M. F., Seyed Abbas Hosseini, and Hamid R. Rabiee. «Epsilon non-Greedy: A Bandit Approach for Unbiased Recommendation via Uniform Data.» 2023 IEEE International Conference on Data Mining Workshops (ICDMW). IEEE, 2023.

Ishikawa, Shion, Young-joo Chung, and Yu Hirate. «Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendation.» arXiv preprint arXiv:2208.11926 (2022).

Namiot, Dmitry, Eugene Ilyushin, and Ivan Chizhov. «The rationale for working on robust machine learning.» International Journal of Open Information Technologies 9.11 (2021): 68-74.

Razvitie transportno-logisticheskih otraslej Evropejskogo Sojuza: otkrytyj BIM, Internet Veshhej i kiberfizicheskie sistemy / V. P. Kuprijanovskij, V. V. Alen’kov, A. V. Stepanenko [i dr.] // International Journal of Open Information Technologies. – 2018. – T. 6, 2. – S. 54-100. – EDN YNIRFG.

Umnaja infrastruktura, fizicheskie i informacionnye aktivy, Smart Cities, BIM, GIS i IoT / V. P. Kuprijanovskij, V. V. Alen’kov, I. A. Sokolov [i dr.] // International Journal of Open Information Technologies. – 2017. – T. 5, 10. – S. 55-86. – EDN ZISODV.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность ИБП для ЦОД СНЭ

ISSN: 2307-8162