Abstract:People share knowledge, experiences and thoughts with the world by using Social Media like blogs, forums, wikis, review sites, social networks, tweets and so on. This has changed the manner in which people communicate and influence social, political and economic behavior of other people in the Web.This work mainly focus on different sentiment analysis techniques a comparative study of different sentiment analysis techniques and a proposed model that uses sentiment analysis on twitter data and user behavior prediction Proposed System mainly rely on Twitter Data.Performing sentiment analysis on twitter data and predicting the behavior of the tweets and thus the user who post those tweets. By analyzing tweets on certain groups the behavior of those groups can also be identified. Social networking websites are considered as major sources of opinions and views of the public on the prevalent social issues at a given point in time. Websites like the Twitter reflect the public views through its millions of messages posted by its users world wide,.By conducting survey these data set required for training data set is being created.and by using these training set twitter commands are analysed and thus the behavior of each tweets are extracted.Based on these tweets if any malicious activities are going on they can be detected and banned.