Emotion Recognition by Textual Tweets Classification Using Voting Classifier

The proliferation of social media platforms has revolutionized sentiment analysis, transforming it into a pivotal research area. Twitter, known for its brevity and real-time engagement, serves as a significant platform for analyzing public opinions on diverse topics. Sentiment analysis leverages machine learning to automatically identify emotions, providing valuable insights into societal trends, government policies, and market dynamics. This study explores the performance of seven machine learning classifiers for emotion detection in tweets, culminating in a novel voting classifier (LR-SGD) that utilizes TF-IDF features. The proposed model achieved a notable accuracy of 79% and an F1 score of 81%.