Sentiment Analysis in Twitter

Diya Sharma, Dhruv Gupta

{2003642, 2003640}

DAV Institute of Engineering & Technology, Jalandhar (India)

{diyasharmaer@gmail.com, dhruv162g@gmail.com}

Abstract

Many of the tweets contain opinions about various subjects. Real-time tweets are categorized as neutral, positive, or negative based on pre-defined tweets. In this paper, we will discuss the Nave Bayes algorithm and its applications for analysing sentiment. The analyser can then give an estimate of the popularity or success of a given subject. The goal of this system is to analyse the sentiment of a Tweet at two levels: the phrase level and the message level. Social organizations may ask people’s opinion on current debates. All this information can be obtained from microblogging services, as their users post their opinions on many aspects of their life regularly. In this work, we present a method which performs 3- class classification of tweet sentiment in Twitter. We present an end to end system which can determine the sentiment of a tweet at two levels- phrase level and message level.. The method first adopts a lexicon based approach to perform entity-level sentiment analysis. This method can give high precision, but low recall. To improve recall, additional tweets that are likely to be opinionated are identified automatically by exploiting the information in the result of the lexicon-based method. A classifier is then trained to assign polarities to the entities in the newly identified tweets. Instead of being labelled manually, the training examples are given by the lexicon-based approach.

Keywords—sentiment analysis, classification, twitter, SVM, feature, experimental results, tweets, Nave bayes