Automatic Detection and Classification of Brand Sentiments on Social Media using Machine Learning Algorithms

Analyzing Brand Sentiments on Twitter using Machine Learning

Abstract

Everyday a large amount of the data is generated by social media, blogs and other media on internet. This huge data contains opinions about the different topics or products or subjects. Opinion of people matters a lot to analyse how the spread of information influence the lives in a large-scale network like Twitter. Data generated by theses websites are unstructured and unorganized which requires processing to generate insights. Natural language processing is used to understand the structure and meaning of human language. Sentiment analysis is one of the major tasks of Natural language processing, where machine learning models are trained to classify text by polarity of opinion (positive, negative). Data used in this research are collected from twitter for reviews on railway services. Different machine learning techniques such as Naïve Bayes, Multinomial Naïve Bayes and support vector machines are used for training and testing the data. The performance of these models are evaluated and compared by using accuracy, precision, recall and F-measure.