Sentiment Analysis of Movie Reviews: A Comparative Study between the Naive-Bayes Classifier and a Rule-based Approach

Abstract

Movie reviews are vital in telling the viewer whether a movie is worth watching or not. They can be classified into textual and non-textual movie reviews. While non-textual movie reviews (stars) give the user information as to how the movie fairs, textual movie reviews give the user a more detailed picture on the positive and negative aspects of the movie. Sentiment Analysis is the use of natural language processing, text analysis, biometrics and computational linguistics to identify, quantify, extract and effectively study states and subjective information given in textual format. This paper aims to conduct sentiment analysis of reviews of movies by using the Naive-Bayes algorithm and compare the results to that of a Rule-Based Approach using the AFINN-111 sentiment dictionary.