Sentiment based multi-index integrated scoring method to improve the accuracy of recommender system

作者：

Highlights：

• Sentiment analysis based on expanded lexicon is proposed to covert sentiment scores.

• Degree classification criteria-based natural noise detection is exploited.

• Multi-index integrated scoring method is used to incorporate ratings and reviews.

• Results reveal that our scheme effectively improves the accuracy of RS.

摘要

•Sentiment analysis based on expanded lexicon is proposed to covert sentiment scores.•Degree classification criteria-based natural noise detection is exploited.•Multi-index integrated scoring method is used to incorporate ratings and reviews.•Results reveal that our scheme effectively improves the accuracy of RS.

论文关键词：Recommender system,Collaborative filtering,Sentiment analysis,Natural noise

论文评审过程：Received 23 December 2020, Revised 23 March 2021, Accepted 21 April 2021, Available online 27 April 2021, Version of Record 10 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115105