Neural text similarity of user reviews for improving collaborative filtering recommender systems
作者：
Highlights：
• Proposing a review-based model to improve collaborative filtering recommender systems.
• Using users’ review similarity in addition to users’ rating in recommender systems.
• Comparing 7 different text representation models including word-based and neural approaches.
• Studying the impact of text similarity models on the performance of the proposed model.
摘要
•Proposing a review-based model to improve collaborative filtering recommender systems.•Using users’ review similarity in addition to users’ rating in recommender systems.•Comparing 7 different text representation models including word-based and neural approaches.•Studying the impact of text similarity models on the performance of the proposed model.
论文关键词：Recommender systems,Natural language processing,Neural text representation,Text similarity,User review
论文评审过程：Received 4 October 2019, Revised 24 October 2020, Accepted 16 November 2020, Available online 25 November 2020, Version of Record 18 December 2020.
论文官网地址：https://doi.org/10.1016/j.elerap.2020.101019
