{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T09:31:25Z","timestamp":1763544685176,"version":"3.45.0"},"reference-count":36,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M773202"],"award-info":[{"award-number":["2025M773202"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Though recommendation systems can help users save time while shopping online, their performance is significantly limited by sparse user data and the inability to capture temporal dynamics of user preferences, such as interest forgetting and topic evolution in reviews. Existing studies primarily focus on static user\u2013item interactions or partial temporal signals (e.g., rating timestamps) but fail to comprehensively model two critical aspects: the non-linear decay of user interests over time, where users gradually forget historical preferences, and the semantic evolution of review topics, which reflects implicit shifts in user preferences across different periods. To address these limitations, we propose a Temporal Dynamic Latent Review-aware Preference Model with Matrix Factorization. Our model integrates an adaptive forgetting-weight function to simulate users\u2019 interest decay and a multi-interval latent topic model to extract evolving preference features from review semantics. Specifically, we design a joint optimization framework that dynamically weights user ratings based on temporal forgetting patterns and decomposes review texts into latent topic factors to alleviate data sparsity. Finally, the experiments employ five baseline methods on six datasets to test the recommendation performance, validating its effectiveness in tracking users\u2019 temporal interest drift and improving recommendation accuracy.<\/jats:p>","DOI":"10.3390\/systems13111034","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T08:50:07Z","timestamp":1763542207000},"page":"1034","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Capturing Dynamic User Preferences: A Recommendation System Model with Non-Linear Forgetting and Evolving Topics"],"prefix":"10.3390","volume":"13","author":[{"given":"Hao","family":"Ding","sequence":"first","affiliation":[{"name":"School of Management, Nanjing University of Posts and Telecommunications, Nanjing, 210003, China"},{"name":"Research Center for Education Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, 210023, China"}]},{"given":"Weiwei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Management, Nanjing University of Posts and Telecommunications, Nanjing, 210003, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1303-363X","authenticated-orcid":false,"given":"Guangwei","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Management, Nanjing University, Nanjing, 210023, China"}]},{"given":"Zhan","family":"Bu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing Audit University, Nanjing, 210023, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"key":"ref_1","first-page":"9898337","article-title":"Design of Personalized News Recommendation System Based on an Improved User Collaborative Filtering Algorithm","volume":"2023","author":"Wang","year":"2023","journal-title":"Mob. Inf. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1287\/ijoc.2022.0194","article-title":"Efficient and flexible long-tail recommendation using cosine patterns","volume":"37","author":"Wang","year":"2025","journal-title":"INFORMS J. Comput."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1007\/s13198-022-01813-z","article-title":"Effective time context based collaborative filtering recommender system inspired by Gower\u2019s coefficient","volume":"14","author":"Jain","year":"2023","journal-title":"Int. J. Syst. Assur. Eng. Manag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103167","DOI":"10.1016\/j.inffus.2025.103167","article-title":"PGA-DRL: Progressive graph attention-based deep reinforcement learning for recommender systems","volume":"121","author":"Tanveer","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.ins.2019.01.076","article-title":"Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model","volume":"484","author":"Parmezan","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"8740207","DOI":"10.1155\/2022\/8740207","article-title":"A Personalized Recommendation Algorithm for Semantic Classification of New Book Recommendation Services for University Libraries","volume":"2022","author":"Pang","year":"2022","journal-title":"Math. Probl. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1287\/ijoc.2023.1286","article-title":"TGVx: Dynamic personalized POI deep recommendation model","volume":"35","author":"Wang","year":"2023","journal-title":"INFORMS J. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"45586","DOI":"10.1109\/ACCESS.2023.3274117","article-title":"Time-Aware Recommender Systems: A Comprehensive Survey and Quantitative Assessment of Literature","volume":"11","author":"Alabduljabbar","year":"2023","journal-title":"IEEE Access"},{"key":"ref_9","unstructured":"Koren, Y. (July, January 28). Collaborative filtering with temporal dynamics. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Paris, France."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xiong, L., Chen, X., Huang, T.K., Schneider, J., and Carbonell, J.G. (May, January 29). Temporal collaborative filtering with bayesian probabilistic tensor factorization. Proceedings of the 2010 SIAM International Conference on Data Mining, Columbus, OH, USA.","DOI":"10.1137\/1.9781611972801.19"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.eswa.2017.01.005","article-title":"Preference dynamics with multimodal user-item interactions in social media recommendation","volume":"74","author":"Rafailidis","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2027","DOI":"10.1587\/transinf.2017EDP7387","article-title":"A novel recommendation algorithm incorporating temporal dynamics, reviews and item correlation","volume":"101","author":"Wu","year":"2018","journal-title":"IEICE Trans. Inf. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, T., Jin, L., Wu, Z., and Chen, Y. (2019). Combined recommendation algorithm based on improved similarity and forgetting curve. Information, 10.","DOI":"10.3390\/info10040130"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"141","DOI":"10.31577\/cai_2020_1-2_141","article-title":"Time-Sensitive Collaborative Filtering Algorithm with Feature Stability","volume":"39","author":"Pang","year":"2020","journal-title":"Comput. Inform."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lv, Y., Zhuang, L., Luo, P., Li, H., and Zha, Z. (2020, January 6\u201310). Time-sensitive collaborative interest aware model for session-based recommendation. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK.","DOI":"10.1109\/ICME46284.2020.9102915"},{"key":"ref_16","unstructured":"Jos\u00e9, E.F., Enembreck, F., and Barddal, J.P. (2020, January 11\u201314). Adadrift: An adaptive learning technique for long-history stream-based recommender systems. Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"116262","DOI":"10.1016\/j.eswa.2021.116262","article-title":"Modeling sentimental bias and temporal dynamics for adaptive deep recommendation system","volume":"191","author":"Rabiu","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, C., Wang, S., Wang, X., and Yao, L. (May, January 30). Modeling temporal positive and negative excitation for sequential recommendation. Proceedings of the ACM Web Conference 2023, Austin, TX, USA.","DOI":"10.1145\/3543507.3583463"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1109\/TCSS.2023.3272633","article-title":"A Deep Recommendation Model Considering the Impact of Time and Individual Diversity","volume":"11","author":"Wu","year":"2023","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3015","DOI":"10.1007\/s10115-020-01447-2","article-title":"Exploiting review embedding and user attention for item recommendation","volume":"62","author":"Sun","year":"2020","journal-title":"Knowl. Inf. Syst."},{"key":"ref_21","unstructured":"Wang, X., Xiao, T., Tan, J., Ouyang, D., and Shao, J. (2020, January 24\u201327). MRMRP: Multi-source review-based model for rating prediction. Proceedings of the Database Systems for Advanced Applications: 25th International Conference, DASFAA 2020, Jeju, Republic of Korea. Proceedings, Part II 25."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107015","DOI":"10.1016\/j.knosys.2021.107015","article-title":"Enhanced review-based rating prediction by exploiting aside information and user influence","volume":"222","author":"Wu","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/j.ins.2020.09.025","article-title":"Learning to utilize auxiliary reviews for recommendation","volume":"545","author":"Hyun","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"117317","DOI":"10.1016\/j.eswa.2022.117317","article-title":"Learning persona-driven personalized sentimental representation for review-based recommendation","volume":"203","author":"Wang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5595","DOI":"10.1007\/s10489-021-02666-y","article-title":"A multi-task dual attention deep recommendation model using ratings and review helpfulness","volume":"52","author":"Liu","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"102842","DOI":"10.1016\/j.ipm.2021.102842","article-title":"A deep recommendation model of cross-grained sentiments of user reviews and ratings","volume":"59","author":"Cai","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"110438","DOI":"10.1016\/j.knosys.2023.110438","article-title":"Enhancing review-based user representation on learned social graph for recommendation","volume":"266","author":"Liu","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"115626","DOI":"10.1016\/j.eswa.2021.115626","article-title":"A novel temporal recommender system based on multiple transitions in user preference drift and topic review evolution","volume":"185","author":"Wangwatcharakul","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1016\/j.physa.2019.04.005","article-title":"Time and ontology for resource recommendation system","volume":"525","year":"2019","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Qiu, G., Bu, J., Liu, K., Han, Y., Wang, C., and Chen, C. (2008, January 21\u201325). Model bloggers\u2019 interests based on forgetting mechanism. Proceedings of the 17th International Conference on World Wide Web, Beijing, China.","DOI":"10.1145\/1367497.1367690"},{"key":"ref_31","first-page":"4213","article-title":"Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation","volume":"7","author":"Yu","year":"2019","journal-title":"IJCAI"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"Lee","year":"1999","journal-title":"Nature"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"9920","DOI":"10.1109\/TKDE.2022.3218994","article-title":"Popularity bias is not always evil: Disentangling benign and harmful bias for recommendation","volume":"35","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Feng, F., He, X., Wei, T., Song, C., Ling, G., and Zhang, Y. (2021, January 11\u201315). Causal intervention for leveraging popularity bias in recommendation. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual.","DOI":"10.1145\/3404835.3462875"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W., and Tucker, A.W. (2013). Nonlinear programming. Traces and Emergence of Nonlinear Programming, Springer.","DOI":"10.1007\/978-3-0348-0439-4_11"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"McAuley, J., and Leskovec, J. (2013, January 12\u201316). Hidden factors and hidden topics: Understanding rating dimensions with review text. Proceedings of the 7th ACM Conference on Recommender Systems, Hong Kong, China.","DOI":"10.1145\/2507157.2507163"}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/11\/1034\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T09:22:13Z","timestamp":1763544133000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/11\/1034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":36,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["systems13111034"],"URL":"https:\/\/doi.org\/10.3390\/systems13111034","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,19]]}}}