Polarity Classification of Twitter Data Using Machine Learning Approach
Waqas Haider Bangyal, Muddesar Iqbal, Ahsan Bashir, George Ubakanma
Abstract
Sentiment analysis has become very important nowadays because there are lots of social media platforms peoples are using to express their opinion. Twitter is one of the most popular social media platforms which is used for microblogs. People use to express their opinion on current affairs, and there is a challenge for researchers to classify the sentiment accurately. In this research study, we proposed a greatly efficient technique for the detection of fake news on covid-19. The data set of fake news is taken from the corpus and executes the NLP cycle. In this research, we applied five machine learning to predict the sentiment of fake or real news. Support Vector Machine, Logistic Regression, KNN, Decision Trees, and Random Forest are machine learning classifiers used in this research, and results are compared.