文章基本信息

标题：DYNAMIC RECOMMENDATION BASED ON USERS' LONG-TERM AND SHORT-TERM PREFERENCES AND SOCIAL IMPACT
本地全文：下载
作者：LI FEI DA ; YIN SI ZHE ; HAN SONG HE 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2021
卷号：99
期号：20
语种：English
出版社：Journal of Theoretical and Applied
摘要：Aiming at the irrationality of existing social recommendation algorithms, such as not fully mining the preference correlation between users and not fully considering the dynamic change of user preferences in time, this paper proposes a dynamic recommendation algorithm based on user long-term and short-term preferences and social influence. From the dynamic change of user preferences and the social relationship of users, the improved gating cycle unit is used to model the user rating information and extract the long-term and short-term preference features; According to the user correlation matrix, the social impact of learning target users is expressed. Experiments on two real datasets show that the proposed algorithm is better than the comparison algorithm.
关键词：Social Recommendation;Preference Learning;Collaborative Filtering;GRU;Recommendation Algorit