A Machine Learning-Based Approach for Sentiment Analysis of Movie Reviews on a Bangladeshi OTT Platform

Abstract

Sentiment analysis is the examination of feelings and viewpoints in any kind of literature. Opinion mining is another phrase for sentiment analysis. The data’s sentiment analysis is quite helpful, to convey the collective, group, or individual viewpoint. This method is employed to ascertain a person’s attitude about a specific source. Huge amounts of data are present on social media and other online platforms in the form of tweets, blogs, status, postings, etc. The movie reviews were examined in this research using a variety of methods. On demand of movies on OTT platform several Facebook reviewer pages has been created in Bangladesh. For this work, almost 1000 Bangla reviews were gathered, containing some English word from Facebook. Customer tones were assessed in movie reviews. We use Unigram, Bigram, and Trigram features with a variety of models, including Decision Tree, Random Forest, Multinomial Naive Bayes, K-Neighbors, and Linear Support Vector Machine in n-grams. Random Forest is the most accurate, with 92.35 percent and 90.03 percent accuracy in Unigram and Trigram, respectively. The most accurate model in Bigram is Decision Tree, which has an accuracy of 89.50 percent. This proposed system will help to analysis reviews and give feedback about a movie.