Published in: Journal of Computer Science and Engineering in Innovations and Research (ISSN No: 3049-1762 online)
Publication Date: June 15, 2026
Pages: 31–34
The people of our society are actively engaged on social media platforms, regularly sharing their opinions and comments on diverse topics. In this research, we analyzed social media posts and tweets using natural language processing (NLP) and machine learning classification algorithms. By categorizing sentiments into positive, negative, and neutral polarities, the proposed model provides valuable insights into public sentiment, societal perspectives, and consumer behavior. Various feature extraction techniques and classifiers are evaluated to optimize sentiment prediction accuracy.
Sentiment Analysis, Natural Language Processing, Machine Learning, Twitter Analysis, Text Classification
Twitter sentiment analysis is the application of machine learning and natural language processing to identify and classify opinions, emotions, and attitudes expressed in user-generated text [1]. With millions of tweets posted daily, social media has become a primary barometer of public opinion regarding products, events, politics, and social issues.
Analyzing this unstructured data presents both significant challenges and enormous opportunities. Challenges stem from the use of informal language, slang, hashtags, emoticons, and abbreviations. This paper implements machine learning workflows for preprocessing Twitter text, extracting sentiment features, and training predictive models to reliably detect sentiment polarity.