Combining Naive Bayes and Adjective Analysis for Sentiment Detection on Twitter

Abstract— Twitter is an emerging platform to express the opinion on various issues. Plenty of approaches like machine learning, information retrieval and NLP have been exercised to figure out the sentiment of the tweets. We have used movie reviews as our data set for training as well as testing and merged the naive bayes and adjective analysis for finding the polarity of the ambiguous tweets. Experimental outputs reveal that the overall accuracy of the process is improved using this model. Firstly we have applied naive bayes on collected tweets which results in set of truly polarized and falsely polarized tweets. False polarized set is further processed with adjective analysis to determine the polarity of tweets and classify it to be positive or negative. Social networking sites in particular twitter and facebook has given us a rostrum to evince our feelings and daily happenings of our life. Twitter, being a microblogging site allows us to exhibit our emotions through tweets. Sentiment classification is a salient task in domain of opinion summarizing, reason mining and products comparisons. Sentiment analysis involves discerning the opinion from the tweets and texts such as movie reviews, product reviews and current trends and analyzing those opinions. These opinions give us the perspective of different user groups. The scale of work that has been done on twitter is increased in a great way. < final year projects >