An Effective Machine Learning Approach for Sentiment Analysis on Popular Restaurant Reviews in Bangladesh

Abstract

Sentiment analysis or text mining is making a huge field of research in this cutting-edge period of social media. Different web journals and Social Media (Facebook, Twitter, Instagram) are the most prevalent stage for the consumers and users where most of the time they express their judgement about trending topics, different brands, restaurant, films, books and so on. Analyzing sentiment is an exceptionally brilliant and viable way to discover people views about news, place, restaurant, film, book, brand. It is helpful for both the owners and sellers. In this study, we built a model using natural language processing techniques and machine learning algorithms to automate the approach of classifying a review on around 200 popular restaurants of Bangladesh as Satisfactory or Poor. This would greatly help the owners to gather a view about the consumers on their restaurant. In this paper, we developed an effective machine learning approach to build a model that can predict the sentiment by analyzing the customer’s review of a restaurant. Our model achieved an accuracy of 95% using Support Vector Machine Classifier besides other classification models.