Sentiment analysis on hotel reviews using Multinomial Naïve Bayes classifier

Abstract

In this modern age where the internet is growing rapidly, the existence of the internet can make it easier for tourist to find any information. In the field of tourism hotel, internet is very helpful in promotion of hotel. Tourists usually tell the experience during the hotel by writing reviews on the internet. Hence many hotel's reviews are found on the internet. The impact on hotel owners is that they can take advantage of reviews on the internet to improve and evaluate their hotels. With the availability of reviews on the internet with large numbers, tourists can't understand all the reviews they read whether they contain positive or negative opinions. It takes a sentiment analysis to quickly detect if the reviews is a positive or negative reviews. This study provides a solution by classifying positive opinion reviews and negative opinions using the Multinomial Naïve Bayes Classifier method and comparing models using preprocessing, feature extraction and feature selection. The best experimental results using preprocessing and feature selection with 10 fold cross validation have an average F1-Score more than 91%.