Sentiment Analysis on Text with Emoticons Using Supervised Algorithm

Use of Social media is on a high level now a days. Everything going to be socially uploaded with a large interest Usually people uses text as well as emotional icons called emoticons to express their emotions. Sentiment Analysis is to show person's emotions, opinion by their reviews or posts. There are already many techniques to show calculations of sentiment analysis by posts or reviews like naive bayes or support vector machine. These gives better result in sentiment analysis field. Existing system uses unsupervised method of polarity calculation to analyze sentiment from text and emoticons. Without use of predefined dictionary it calculates polarity on the basis of presence of emoticons. However it restrict presence of emoticons to classify text and analyze sentiment. Proposed system works on Supervised learning method. It reduces restriction of presence of emoticons in existing system. It can work on only text, only emoticons as well as combination of both. Preprocessing steps contains feature extraction and removal of stop words. Here c5 classifier has been used for better accuracy and classify posts by rule-set.