查看文章

Sentiment Analysis is an important and a very active area of research. It is being used by various public and nonpublic organizations to find out sentiments of the web users about their product and services, which results in making some important and effective decisions. The sudden growth of social media applications has resulted in the generation of a huge amount of opinionated data which is mostly being used in research work. Sentiment Analysis is a sub-discipline of natural language processing, where the main idea is to understand polarity of a sentence, paragraph or whole document by analysis of textual data gathered from various sources. This paper is giving a comparative analysis of four supervised machine learning techniques (Support Vector Machine, Naive Bayes, Decision Tree and Neural Network) used for sentiment analysis on the basis of different performance parameters. In this comparative study, it is analyzed that SVM (Support Vector Machine) has greater performance than other three supervised machine learning techniques.