Multi-Aspect Sentiment Analysis Hotel Review Using RF, SVM, and Naïve Bayes based Hybrid Classifier

In the hotel tourism sector, of course, it cannot be separated from role social media because tourists tend to share experiences about services and products offered by a hotel, such as adding pictures, reviews, ratings which will helpful references for other tourists, example on online TripAdvisor. However, tourists' many regarding make some people feel confused in determining right visit. Therefore, this study, an aspect-based analysis reviews hotels is carried out, easier determine based best category aspects. The dataset used TripAdvisor Hotel Reviews already Kaggle website. And has five aspects, namely Room, Location, Cleanliness, Registration, Service. A review was out into positive negative categories using Random Forest, SVM, Naive Bayes Hybrid Classifier methods solve problem. study method gets better accuracy than classification one algorithm multi-aspect data, got average 84%, Naïve 82.4%, Forest 82.2%, use SVM 81%