Tensor factorization method based on review text semantic similarity for rating prediction

作者：

Highlights：

• A Tensor factorization method based on review texts semantic similarity.

• Review texts helps to accurately classify users with most similar preferences.

• Text similarity well reflects preferences compared to review topics, opinion.

• Experimental results show that our model achieves better performance.

摘要

•A Tensor factorization method based on review texts semantic similarity.•Review texts helps to accurately classify users with most similar preferences.•Text similarity well reflects preferences compared to review topics, opinion.•Experimental results show that our model achieves better performance.

论文关键词：Tensor factorization,Semantic similarity,User reviews,Rating prediction

论文评审过程：Received 2 April 2018, Revised 21 June 2018, Accepted 29 July 2018, Available online 31 July 2018, Version of Record 7 September 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.07.059