Why do people (not) like me?: Mining opinion influencing factors from reviews

作者：

Highlights：

• A novel feedback-based recommendation idea is introduced for service providers.

• Reasons why people like or do not like something are discovered via semantic rules.

• Factors that lead to a change in the opinions are analyzed.

• Full processing pipeline to improve recommendation systems is proposed.

摘要

•A novel feedback-based recommendation idea is introduced for service providers.•Reasons why people like or do not like something are discovered via semantic rules.•Factors that lead to a change in the opinions are analyzed.•Full processing pipeline to improve recommendation systems is proposed.

论文关键词：Text mining,Opinion mining,Causality analysis,Feedback-based recommendations

论文评审过程：Received 27 July 2016, Revised 2 October 2016, Accepted 3 October 2016, Available online 8 October 2016, Version of Record 25 October 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.10.001