Comparative Analysis of Machine Learning Models for Sentiment Analysis of Twitter Data

Sentiment Analysis plays a pivotal role in modern business operations, including analyzing and monitoring textual data. This paper presents a comparative analysis of various machine learning models for sentiment analysis of Twitter data. The models explored include Decision Tree, KNN classifier, Logistic Regression, Multinomial Naïve Bayes, and Random Forest Classifier. Emphasizing the significance of preprocessing and vectorization techniques for feature extraction, the study delves into hyperparameter tuning to optimize each model’s performance. Evaluation metrics such as accuracy, precision, recall, F1 score, and ROC analysis highlight the Random Forest Classifier demonstrating the highest accuracy. These findings underscore the efficacy of machine learning methodologies in sentiment analysis tasks and offer valuable insights for enhancing model performance in real-world applications.