{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T23:26:25Z","timestamp":1787959585106,"version":"build-2784847793"},"reference-count":30,"publisher":"World Scientific Pub Co Pte Ltd","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2026,9,15]]},"abstract":"<jats:p>Algorithmic bias in recommendation systems can lead to unfair treatment of users or underrepresentation of certain groups, which has become a critical concern in online platforms, potentially resulting in significant societal impacts such as discrimination and commercial losses due to reduced user trust and platform engagement. In this paper, we propose FAIR-RL, a fairness-aware deep reinforcement learning framework that mitigates bias while maintaining recommendation quality. Unlike traditional recommendation approaches that focus solely on predictive accuracy, our method incorporates a fairness-sensitive reward function that balances user engagement with group-level fairness. In contrast to existing fairness-aware recommendation methods, which typically address fairness in isolation, FAIR-RL combines fairness and performance in a unified, dynamic framework, ensuring better adaptability to evolving user preferences. The framework employs a dual-policy network: one policy optimizes individual user satisfaction, while the other enforces fairness constraints across diverse user groups. Additionally, dynamic reward adjustment allows the system to adaptively reduce bias in real-time recommendation scenarios. Experimental results on benchmark datasets demonstrate that FAIR-RL significantly improves fairness metrics without sacrificing recommendation performance, providing an effective solution for equitable personalized recommendations.<\/jats:p>","DOI":"10.1142\/s0218001426520099","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T08:24:54Z","timestamp":1775463894000},"source":"Crossref","is-referenced-by-count":1,"title":["Fairness-Aware Deep Reinforcement Learning for Mitigating Algorithmic Bias in Recommendation Systems"],"prefix":"10.1142","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2622-0472","authenticated-orcid":false,"given":"Hui","family":"Zhi","sequence":"first","affiliation":[{"name":"School of Journalism and Communication, Hubei University of Education, Wuhan 430205, Hubei, P.\u00a0R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2534-6003","authenticated-orcid":false,"given":"Ling","family":"Xin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hubei Science and Technology College, Wuhan 430074, Hubei, P.\u00a0R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4264-334X","authenticated-orcid":false,"given":"Shifeng","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Law and Joumalism and Communication, Wuhan Donghu College, Wuhan 430212, P.\u00a0R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"219","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"S0218001426520099BIB001","unstructured":"N. Asghar, Yelp dataset challenge: Review rating prediction, preprint (2016), arXiv:1605.05362."},{"key":"S0218001426520099BIB002","unstructured":"J. Bennett and S. Lanning, The netflix prize (2007)."},{"key":"S0218001426520099BIB003","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330745"},{"key":"S0218001426520099BIB004","first-page":"834","volume-title":"Proc. 12th ACM Int. Conf. Web Search and Data Mining","author":"Bird S.","year":"2019"},{"key":"S0218001426520099BIB005","volume-title":"Music Recommendation and Discovery in the Long Tail","author":"Celma Herrada \u00d2.","year":"2009"},{"key":"S0218001426520099BIB006","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA49011.2020.00083"},{"key":"S0218001426520099BIB007","unstructured":"Y. Deldjoo, V. W. Anelli, H. Zamani, A. Bellog\u00edn and T. Di Noia, Recommender systems fairness evaluation via generalized cross entropy, preprint (2019), arXiv:1908.06708."},{"key":"S0218001426520099BIB008","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2025.3583947"},{"key":"S0218001426520099BIB009","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"S0218001426520099BIB010","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"S0218001426520099BIB011","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101906"},{"key":"S0218001426520099BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2011.83"},{"key":"S0218001426520099BIB013","doi-asserted-by":"publisher","DOI":"10.1145\/3495163"},{"key":"S0218001426520099BIB014","doi-asserted-by":"crossref","unstructured":"W. Liu, F. Liu, R. Tang, B. Liao, G. Chen and P. A. Heng, Balancing accuracy and fairness for interactive recommendation with reinforcement learning, preprint (2021), arXiv:2106.13386.","DOI":"10.1007\/978-3-030-47426-3_13"},{"key":"S0218001426520099BIB015","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3587617"},{"key":"S0218001426520099BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3521195"},{"key":"S0218001426520099BIB017","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533136"},{"key":"S0218001426520099BIB018","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113392"},{"key":"S0218001426520099BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3640136"},{"key":"S0218001426520099BIB020","first-page":"1","author":"Pei J.","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"S0218001426520099BIB021","first-page":"1","author":"Pei J.","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"S0218001426520099BIB022","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31718"},{"key":"S0218001426520099BIB023","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220088"},{"key":"S0218001426520099BIB024","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-022-00136-w"},{"key":"S0218001426520099BIB025","doi-asserted-by":"publisher","DOI":"10.1016\/j.jer.2024.06.016"},{"key":"S0218001426520099BIB026","doi-asserted-by":"publisher","DOI":"10.1145\/3547333"},{"key":"S0218001426520099BIB027","first-page":"2925","volume":"30","author":"Yao S.","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001426520099BIB028","first-page":"325","volume-title":"Proc. Int. Conf. Machine Learning","author":"Zemel R.","year":"2013"},{"key":"S0218001426520099BIB029","doi-asserted-by":"crossref","unstructured":"X. Zhao, L. Zhang, L. Xia, Z. Ding, D. Yin and J. Tang, Deep reinforcement learning for list-wise recommendations, preprint (2017), arXiv:1801.00209.","DOI":"10.1145\/3240323.3240374"},{"key":"S0218001426520099BIB030","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060754"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001426520099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:00:32Z","timestamp":1780372832000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001426520099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":30,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,9,15]]}},"alternative-id":["10.1142\/S0218001426520099"],"URL":"https:\/\/doi.org\/10.1142\/s0218001426520099","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"article-number":"2652009"}}