Deriving customer preferences for hotels based on aspect-level sentiment analysis of online reviews

作者：

Highlights：

• A systematic approach for deriving customer preferences from online hotel reviews is proposed.

• A specific triple is defined to represent the sentiment elements of a review comment.

• An algorithm is developed for sentiment analysis of implicit hotels’ attributes.

• Word embedding, co-occurrence and dependency parsing are combined.

• Online hotel reviews crawled from Ctrip.com are used to verify the proposed approach.

摘要

•A systematic approach for deriving customer preferences from online hotel reviews is proposed.•A specific triple is defined to represent the sentiment elements of a review comment.•An algorithm is developed for sentiment analysis of implicit hotels’ attributes.•Word embedding, co-occurrence and dependency parsing are combined.•Online hotel reviews crawled from Ctrip.com are used to verify the proposed approach.

论文关键词：Customer preferences,Online hotel reviews,Fine-grained sentiment analysis,Word embedding,Dependency parsing

论文评审过程：Received 29 March 2021, Revised 3 September 2021, Accepted 13 September 2021, Available online 15 September 2021, Version of Record 30 September 2021.

论文官网地址：https://doi.org/10.1016/j.elerap.2021.101094