A hybrid method for text-based sentiment analysis

Abstract

Text-based sentiment analysis is an automated process of analyzing natural language text data and classifying opinions as negative, positive or neutral using computational methods. It can assist in search engines, recommender systems, marketing research, and particularly with online business. With the growth of the internet, numerous business websites have been deployed to support online shopping products, booking services as well as to allow online reviewing and commenting the services in forms of either business forums or social networks. Use of sentiment analysis for automatically mining opinion using the feedbacks from such emerging internet platforms is not only useful for customers seeking for advice, but also necessary for business to study customers' attitudes toward brands, products, services, or events, and has become an increasingly dominant trend in business strategic management. Current state-of-the-art approaches for sentiment analysis include lexicon based and machine learning based methods. In this research, we proposed a hybrid method that utilizes lexicon based approach with machine learning. We showed that our method outperformed the state-of-the-art lexicon based methods.