Topic-based sentiment analysis of hotel reviews

ABSTRACT

We developed a system for sentiment analysis of hotel reviews. The system uses topics to give accurate reports related to some qualities specified by the end-user. This system permits users to evaluate a given hotel services quality according to multiple criteria. Besides, a user can make different detailed comparisons between hotels. To achieve this goal, the proposed system decomposes complex opinions into sub-comments to extract the specified concept. Further, it translates non-English comments into the English language. After having tested the system by using two datasets, the obtained results are judged to be satisfactory.

KEYWORDS:

• Word tree
• sentiment analysis
• hotel reviews
• opinion mining
• data analysis

Acknowledgements

Many thanks to Pr. Amer Draa.

Disclosure statement

No potential conflict of interest was reported by the author(s).