Sentiment Analysis and Classification of Restaurant Reviews using Machine Learning

Abstract

In the last few years use of social networking sites has increased tremendously. People use social media platforms to share their views on almost all subjects. These views are in various forms like, blogs, tweets, Facebook posts, online discussion boards, Instagram posts, etc. Sentiment analysis deals with the process of computationally defining and classifying the views expressed in the comment, post or document. Typically, the aim of sentiment analysis is to find out the customer's attitude towards a product or service. Customers' feedback is vital for businesses, and social media being a powerful platform, can be used to improve and enhance business opportunities if the feedback on social media can be analyzed timely. Therefore, the focus of this paper is to analyze the customer reviews about various restaurants across Karachi - one of the biggest cities of Pakistan. For this research, customer reviews are collected from a very popular Facebook community- the SWOT'S guide to Karachi's restaurants. The contribution of this research is twofold. First, it performs sentiment analysis and classifies each comment as positive, negative. Second, by using text categorization techniques, comments are automatically classified according to feedback about food taste, ambiance, service, and value for money. A manually annotated dataset of around 4000 records was used for training and testing. Several algorithms were used for classification, including Naive Bayes Classifier, Logistic Regression, Support Vector Machine (SVM), and Random Forest. The performance comparison of these algorithms is presented. The best results, that is 95% accuracy, were achieved by using a random forest algorithm.