COMPARATIVE STUDY ON MACHINE LEARNING APPROACHES FOR TEXT CLASSIFICATION

Abstract

Text Classification is the field of study that analyzes people’s opinions, sentiments, evaluations, appraisals, attitudes, and emotions towards entities such as products, services, organizations, individuals, issues, events, topics, and their attributes. It has thus become a necessity to collect and study opinions on the Web. Of course, there are opinionated publications outside of the Web as well, and many organizations also collect consumer feedback from emails, call centers, and surveys to gauge what their customers think of their products. there are many classifier systems used for predicting the polarity of collected data while using Machine Learning (ML) algorithms. Our project is to essentially evaluate different ML models like Random Forest Classifier, Logistic Regression, and Decision Tree Classifier designed for text classification using different algorithms and analyze the performance of each model. To build our model, we use the Twitter dataset. Further data extraction, processing, and modeling are done on the dataset before using it for training the models. then models are evaluated and compared with other models based on their performance