A Hotel Ranking Model Through Online Reviews With Aspect-Based Sentiment Analysis

Abstract

The number of online textual reviews on each hotel aspect can reflect the tourist preference difference on distinct aspects. Therefore, not only online textual reviews but their numbers have a significant impact on tourists’ hotel selection decisions. Motivated by this observation, this study proposes a hotel ranking model for hotel selection based on the sentiment analysis of online textual reviews by considering the differences in the number of reviews on different aspects. We explicitly model the differences in the number of reviews on aspects through the confidence interval estimation. In addition, the AS-Capsules model, which can jointly perform aspect detection and aspect-level sentiment classification with high accuracy, is employed for sentiment analysis. We conducted a case study on TripAdvisor.com, the experimental results show that our proposed model is able to effectively assist the tourists in making the desirable decision on hotel selection.