Sentiment Analysis with NLP on Twitter Data

Abstract

Every social networking sites like facebook, twitter, instagram etc become one of the key sources of information. It is found that by extracting and analyzing data from social networking sites, a business entity can be benefited in their product marketing. Twitter is one of the most popular sites where people used to express their feelings and reviews for a particular product. In our work, we use twitter data to analyze public views towards a product. Firstly, we have developed a natural language processing (NLP) based pre-processed data framework to filter tweets. Secondly, we incorporate Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) model concept to analyze sentiment. This is an initiative to use BoW and TFIDF are used together to precisely classify positive and negative tweets. We have found that by exploiting TF-IDF vectorizer, the accuracy of sentiment analysis can be substantially improved and simulation results show the efficiency of our proposed system. We achieved 85.25% accuracy in sentiment analysis using NLP technique.