Sentiment Analysis of National Eligibility-Cum Entrance Test on Twitter Data Using Machine Learning Techniques

Abstract

People around the world use social media to communicate and share their perceptions about a variety of topics. Social media analysis is crucial to interacting, distributing, and stating people's opinions on various topics. Governments and organizations can take action on alarming issues more quickly with the help of such textual data investigation. The key purpose of this effort is to perform sentiment analysis of textual data regarding National Eligibility-cum Entrance Test (NEET), perform classification and determine how people feel about NEET. In this study, 11 different machine learning classifiers were used to analyze tweet sentiment, along with natural language processing (NLP). Tweepy is the python library which is used to get user opinion about NEET Exam. Annotating the data is accomplished using TextBlob and Vader. Text data is pre-processed with a natural language toolkit. The dataset downloaded from Twitter shows that unigram models perform well compared to bigram and trigram models. TF-IDF models are more accurate than count vectorizer which is based on word frequency. classifier achieves an average accuracy of 92%. Perceptron also receives the uppermost average accuracy of 91%. According to the data from the experiment, most people have a neutral opinion of NEET.