Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{192881,
        author = {Pallavi Subhash Malode and DR. K.D. KHARAT},
        title = {Social media-based Sentiment Analysis Using NLP and Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {3952-3957},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192881},
        abstract = {The exponential rise of political news content across digital platforms has intensified the need for automated methods to analyze sentiment embedded in textual narratives. Manual inspection is neither scalable nor consistent, particularly when handling large volumes of ideologically diverse articles. This study presents a supervised learning–based sentiment analysis framework optimized for classifying political news into positive, negative, and neutral categories. The system employs a structured pipeline integrating preprocessing, tokenization, part-of-speech tagging, named entity recognition, aspect extraction, and machine-learning classification. Algorithms including Naïve Bayes, Support Vector Machine (SVM), and a proposed optimized model were evaluated using curated political news datasets. Experimental findings indicate that the optimized model outperforms standard classifiers, achieving 88% precision, 96% recall, 92% F-score, and 87% accuracy, demonstrating its reliability in detecting sentiment within complex political narratives. The work contributes to political communication research by providing a scalable NLP-based solution capable of identifying media bias, assessing public opinion, and supporting data-driven policy analysis.},
        keywords = {},
        month = {February},
        }