TWITTER SENTIMENT ANALYSIS WITH ENHANCED REDUCTION OPTIMIZATION

Abstract

Sentiment analysis is basically concerned with analysis of emotions and opinions from text. We can refer sentiment analysis as opinion mining. Sentiment analysis finds and justifies the sentiment of the person with respect to a given source of content. Social media contain huge amount of the sentiment data in the form of tweets, blogs, and updates on the status, posts, etc. Sentiment analysis of this largely generated data is very useful to express the opinion of the mass. Twitter sentiment analysis is tricky as compared to broad sentiment analysis because of the slang words and misspellings and repeated characters. We know that the maximum length of each tweet in Twitter is 140 characters. So it is very important to identify correct sentiment of each word. In our project we are proposing a highly accurate model of sentiment analysis of tweets with respect to latest reviews of upcoming Bollywood or Hollywood movies. With the help of feature vector and classifiers such as Support vector machine and Nae Bayes, we are correctly classifying these tweets as positive, negative and neutral to give sentiment of each tweet. To correctly classify the tweets machine learning technique uses the training data. So, this technique does not require the database of words like used in knowledge-based approach and therefore, machine learning techniques is better and faster.The several methods are used to extract the feature from the source text. Feature extraction is done in two phases: In the first phase extraction of data related to twitter is done i.e. twitters specific data is extracted. Now by doing this, the tweet is transformed into normal text. In the next phase, more features are extracted and added to feature vector. Each tweet in the training data is associated with class label. This training data is passed to different classifiers and classifiers are trained.