IMPROVING OPINION MINING OF SOCIAL MEDIA POLITICAL CONTENT

Abstract

Twitter is a micro-blogging website that provides a platform for people to share and express their views about topics, happenings, products, and other services. In numerous fields of standard dialect handling, past investigations of feeling acknowledgment on Twitter, for the most part, centered around the utilization of vocabularies and straightforward classifiers on the pack of words models. Tweets can be characterized into various classes dependent on their pertinence with the point looked. The existing system creates only three significant emotions labeled data sets corresponding to different classification of emotions. Automatic sentiment analysis and opinion mining of texts collected from social networks based on political tweets and microblogging websites are oriented toward the binary classification (i.e., classification into "positive" and "negative") or classification into "positive," "negative," and "neutral" (i.e., the ternary classification) of texts. Classification and result are not more accurate as compared to the proposed system. Most active topics are not mentioned in the existing system.