Sentiment Analysis on Social Media Tweets Using Machine Learning

Abstract

Social media platforms have become integral channels for communication and expression, attracting significant attention from professionals across various sectors, including leadership, decision-making, and consulting.Leveraging the wealth of user-generated content on platforms such as Twitter, Facebook, and others, researchers are exploring methods to predict public opinion on diverse topics.In this study, we utilized Twitter data sourced through the "tweepy" API, focusing on tweets of Indian origin.Through live streaming of tweets, we collected a dataset accessible via secret keys and access tokens.Employing machine learning algorithms including Naive Bayes, Maximum Entropy, KNN, and SVM, we assigned sentiment scores to individual tweets, facilitating the analysis of public opinion dynamics.Our findings underscore the potential of machine learningbased sentiment analysis in extracting valuable insights from social media data, offering opportunities for informed decision-making in various domains.