期刊
IEEE ACCESS
卷 10, 期 -, 页码 6218-6245出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3140121
关键词
Recommender systems; Collaborative filtering; Urban areas; Predictive models; Licenses; Sparse matrices; Motion pictures; Collaborative filtering; group recommender systems; recommender systems
资金
- Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam
To meet the demand for group activities, single-user recommender systems need to be scaled up. This paper introduces the concept of deep profiles and proposes group recommendation methods based on deep profile aggregation. Experiments have shown that group recommendations based on deep profiles are more efficient.
To meet the increasing demand for group activities, single-user recommender systems need to be scaled up to provide recommendations to groups of users. This issue is solved by aggregating item preference profiles of individual group members into a single item preference profile, thereby allowing recommendations to be created for this item preference profile. In this paper, we introduce the concept of deep profiles of users, and we propose group recommendation methods based on the aggregation of group members' deep profiles, instead of item preference profiles as in previous studies. The term deep profile refers to the users' profiles that lie deep within the recommendation algorithms. Experiments have shown that group recommendations based on deep profiles give higher efficiency in terms of F1-score and nDCG than those based on item preference profiles.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据