Machine Learning Based Sentiment Analysis on Twitter Data

Abstract

With the increase of social networking epoch and its growth, the net has become one in all the powerful platforms for online learning, exchanging ideas and sharing opinions. Social media contain an enormous amount of the info for sentiment analysis within the type of tweets, blogs, and updates on the status, posts, etc.This paper addresses the matter of sentiment analysis in twitter; that's classifying tweets in keeping with the sentiment into positive, negative or neutral. Analysing the emotions of the general public became important to seek out the reviews of the shoppers for any product within the market, predicting political elections and predicting socio economic phenomena like stock market. The aim of this project is to develop a functional classifier for accurate and automatic sentiment classification of an unknown tweet stream by using convolutional neural networks. IndexTerms – Twitter, Sentiment, Natural Language Processing, CNN.