2. IMPLEMENTATION OF MACHINE LEARNING CLASSIFIER TO CLASSIFY THE USER COMMENTS ON SOCIAL MEDIA

Now a days the Internet facility is full of information pertaining to opinion of people through applications, for example, web -based media, miniature contributing to a blog destinations, audit locales, individual web journals and so on Nostalgic investigation is a region in text mining where assessment of individuals can be broke down and arranged in to positive, negative or unbiased. In this work, the estimations of the tweets or audits distributed in the twitter is recognized via looking for the specific catchphrase in tweets and afterward assess the extremity of the tweets as certain and negative. T he estimations of the tweets that are tweeted on a twitter assessed dependent on include choice of each score words. To choose the best highlights Naive Bayes Classifier (NBC) is utilized for preparing and testing the highlights of a words and furthermore assessing the notion extremity of each tweets. Performance evaluation parameters such as accuracy, precision and time is taken into consideration and compared with three machine learning classifiers, namely, Random Forest, Naive Bayes and Support Vector Machine(SVM) .