Alleviating data sparsity problem in time-aware recommender systems using a reliable rating profile enrichment approach
作者：
Highlights：
• A probabilistic model is proposed to evaluate user’s rating profile.
• Temporal reliability and confidence measures are used to design recommender systems.
• Changing of users’ preferences over time is considered in the proposed method.
• The reliability measure is used to evaluate the quality of the predictions.
• The confidence measure is used to identify ineffective users from neighbors set.
摘要
•A probabilistic model is proposed to evaluate user’s rating profile.•Temporal reliability and confidence measures are used to design recommender systems.•Changing of users’ preferences over time is considered in the proposed method.•The reliability measure is used to evaluate the quality of the predictions.•The confidence measure is used to identify ineffective users from neighbors set.
论文关键词：Recommender system,Data sparsity,Reliability,Confidence,Temporal information,Collaborative filtering
论文评审过程：Received 8 December 2020, Revised 16 July 2021, Accepted 31 August 2021, Available online 4 September 2021, Version of Record 15 September 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115849
