SENTIMENT ANALYSIS IN TURKISH FILM COMMENTS

Abstract

Analysing the sentiments in text files, movie website's user comment is an important research fields both for companies and the academics due to the challenges and opportunities it possesses. In this study, we applied lexicon based method and Machine learning algorithms that are support vector machine, naive bayes, logistic regression and decision tree methods to various sized Turkish datasets. As a result, we observed that the Logistic Regression algorithm gave the best result with an accuracy of %77.35