TWIX: Balancing Fairness and Utility in Item Exposure for Recommendation Systems
Resumo
Recommendation systems personalize user experiences but often introduce the “rich-get-richer” effect, where popular items dominate visibility. This bias disadvantages new items or those with few interactions, where historical data limits the exposure of new items. To address these challenges, fairness in exposure has been studied through balanced exposure, which ensures equal visibility but may reduce recommendation utility, and quality-weighted exposure, which prioritizes high-quality items. To mitigate the trade-off between fairness and utility, we propose TWIX, a method that applies quality-weighted and balanced exposures determined by a threshold. Our approach reduces popularity bias and cold start issues while maintaining recommendation utility.
Palavras-chave:
recommendation systems, popularity bias, fairness of exposure
Referências
Abdollahpouri, H., Burke, R., and Mobasher, B. (2017). Controlling popularity bias in learning-to-rank recommendation. In Proceedings of the eleventh ACM conference on recommender systems, pages 42–46.
Abdollahpouri, H., Mansoury, M., Burke, R., and Mobasher, B. (2019). The unfairness of popularity bias in recommendation. arXiv preprint arXiv:1907.13286.
Biega, A. J., Gummadi, K. P., and Weikum, G. (2018). Equity of attention: Amortizing individual fairness in rankings. In The 41st international acm sigir conference on research & development in information retrieval, pages 405–414.
Boratto, L., Fenu, G., and Marras, M. (2021). Connecting user and item perspectives in popularity debiasing for collaborative recommendation. Information Processing & Management, 58(1):102387.
Celma, O. (2010). Music Recommendation and Discovery in the Long Tail. Springer.
Do, V., Corbett-Davies, S., Atif, J., and Usunier, N. (2021). Two-sided fairness in rankings via lorenz dominance. Advances in Neural Information Processing Systems, 34:8596–8608.
Frank, M., Wolfe, P., et al. (1956). An algorithm for quadratic programming. Naval research logistics quarterly, 3(1-2):95–110.
Harper, F. M. and Konstan, J. A. (2015). The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):1–19.
Järvelin, K. and Kekäläinen, J. (2002). Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems (TOIS), 20(4):422–446.
Khenissi, S. and Nasraoui, O. (2020). Modeling and counter-acting exposure bias in recommender systems. arXiv preprint arXiv:2001.04832.
Koren, Y., Bell, R., and Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8):30–37.
Merton, R. K. (1968). The matthew effect in science: The reward and communication systems of science are considered. Science, 159(3810):56–63.
Morik, M., Singh, A., Hong, J., and Joachims, T. (2020). Controlling fairness and bias in dynamic learning-to-rank. In Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, pages 429–438.
Natarajan, S., Vairavasundaram, S., Natarajan, S., and Gandomi, A. H. (2020). Resolving data sparsity and cold start problem in collaborative filtering recommender system using linked open data. Expert Systems with Applications, 149:113248.
Ni, J., Li, J., and McAuley, J. (2019). Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pages 188–197.
Sang, S., Ma, M., and Pang, H. (2024). Weighted matrix factorization recommendation model incorporating social trust. Applied Sciences, 14(2):879.
Singh, A. and Joachims, T. (2018). Fairness of exposure in rankings. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2219–2228.
Usunier, N., Do, V., and Dohmatob, E. (2022). Fast online ranking with fairness of exposure. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pages 2157–2167.
Wu, Y., Cao, J., Xu, G., and Tan, Y. (2021). Tfrom: A two-sided fairness-aware recommendation model for both customers and providers. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pages 1013–1022.
Yin, H., Cui, B., Li, J., Yao, J., and Chen, C. (2012). Challenging the long tail recommendation. arXiv preprint arXiv:1205.6700.
Abdollahpouri, H., Mansoury, M., Burke, R., and Mobasher, B. (2019). The unfairness of popularity bias in recommendation. arXiv preprint arXiv:1907.13286.
Biega, A. J., Gummadi, K. P., and Weikum, G. (2018). Equity of attention: Amortizing individual fairness in rankings. In The 41st international acm sigir conference on research & development in information retrieval, pages 405–414.
Boratto, L., Fenu, G., and Marras, M. (2021). Connecting user and item perspectives in popularity debiasing for collaborative recommendation. Information Processing & Management, 58(1):102387.
Celma, O. (2010). Music Recommendation and Discovery in the Long Tail. Springer.
Do, V., Corbett-Davies, S., Atif, J., and Usunier, N. (2021). Two-sided fairness in rankings via lorenz dominance. Advances in Neural Information Processing Systems, 34:8596–8608.
Frank, M., Wolfe, P., et al. (1956). An algorithm for quadratic programming. Naval research logistics quarterly, 3(1-2):95–110.
Harper, F. M. and Konstan, J. A. (2015). The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):1–19.
Järvelin, K. and Kekäläinen, J. (2002). Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems (TOIS), 20(4):422–446.
Khenissi, S. and Nasraoui, O. (2020). Modeling and counter-acting exposure bias in recommender systems. arXiv preprint arXiv:2001.04832.
Koren, Y., Bell, R., and Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8):30–37.
Merton, R. K. (1968). The matthew effect in science: The reward and communication systems of science are considered. Science, 159(3810):56–63.
Morik, M., Singh, A., Hong, J., and Joachims, T. (2020). Controlling fairness and bias in dynamic learning-to-rank. In Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, pages 429–438.
Natarajan, S., Vairavasundaram, S., Natarajan, S., and Gandomi, A. H. (2020). Resolving data sparsity and cold start problem in collaborative filtering recommender system using linked open data. Expert Systems with Applications, 149:113248.
Ni, J., Li, J., and McAuley, J. (2019). Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pages 188–197.
Sang, S., Ma, M., and Pang, H. (2024). Weighted matrix factorization recommendation model incorporating social trust. Applied Sciences, 14(2):879.
Singh, A. and Joachims, T. (2018). Fairness of exposure in rankings. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2219–2228.
Usunier, N., Do, V., and Dohmatob, E. (2022). Fast online ranking with fairness of exposure. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pages 2157–2167.
Wu, Y., Cao, J., Xu, G., and Tan, Y. (2021). Tfrom: A two-sided fairness-aware recommendation model for both customers and providers. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pages 1013–1022.
Yin, H., Cui, B., Li, J., Yao, J., and Chen, C. (2012). Challenging the long tail recommendation. arXiv preprint arXiv:1205.6700.
Publicado
29/09/2025
Como Citar
M. SILVA, Maria de Lourdes; CHAVES, Iago C.; MENDONÇA, André L. C.; D. NETO, Eduardo R.; MACHADO, Javam de Castro.
TWIX: Balancing Fairness and Utility in Item Exposure for Recommendation Systems. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 40. , 2025, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 427-440.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2025.247259.
