Do adjective features from user reviews address sparsity and transparency in recommender systems?

作者：

Highlights：

• Adjective features embedded in user reviews can be utilized for recommendation.

• An effective method for extracting useful adjective features is proposed.

• The SVD method is extended to incorporate adjective features.

• The proposed method is able to alleviate the data sparsity and transparency problems.

摘要

•Adjective features embedded in user reviews can be utilized for recommendation.•An effective method for extracting useful adjective features is proposed.•The SVD method is extended to incorporate adjective features.•The proposed method is able to alleviate the data sparsity and transparency problems.

论文关键词：Adjective features,Recommender systems,Side information,Sparsity,Transparency,User reviews

论文评审过程：Received 25 October 2017, Revised 21 April 2018, Accepted 21 April 2018, Available online 24 April 2018, Version of Record 27 April 2018.

论文官网地址：https://doi.org/10.1016/j.elerap.2018.04.002