Sentiment Analysis of Tweets Using Machine Learning Approach

Abstract

Microblogging websites like Twitter and Facebook, in this new era, is loaded with opinions and data. One of the most widely used micro-blogging site, Twitter, is where people share their ideas in the form of tweets and therefore it becomes one of the best sources for sentimental analysis. Opinions can be widely grouped into three categories good for positive, bad for negative and neutral and the process of analyzing differences of opinions and grouping them in all these categories is known as Sentiment Analysis. Data mining is basically used to uncover relevant information from web pages especially from the social networking sites. Merging data mining with other fields like text mining, NLP and computational intelligence we are able to classify tweets as good, bad or neutral. The main emphasis of this research is on the classification of emotions of tweets' data gathered from Twitter. In the past, researchers were using existing machine learning techniques for sentiment analysis but the results showed that existing machine learning techniques were not providing better results of sentiment classification. In order to improve classification results in the domain of sentiment analysis, we are using ensemble machine learning techniques for increasing the efficiency and reliability of proposed approach. For the same, we are merging Support Vector Machine with Decision Tree and experimental results prove that our proposed approach is providing better classification results in terms of f-measure and accuracy in contrast to individual classifiers.