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{177329,
        author = {Saniya Mastan Kadmude and Shrutika Dattu Bansode and Vedant Sanjay Joge and Prof. Prachi Tamhan},
        title = {Social Media Insights},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {1788-1797},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177329},
        abstract = {This study introduces a novel machine learning approach for sentiment analysis in social media comments, classifying user expressions into positive, negative, or neutral categories. As platforms surpass 1 billion active users, the massive volume of unstructured feedback presents challenges such as scalability, informal language variations, emoji interpretation, sarcasm detection, and spam filtering. To address these, the research utilizes a curated dataset of 18,500 manually annotated text samples, processed using advanced normalization techniques to enhance reliability.
Four classification models Naïve Bayes, SVM, Gradient Boosting, and Random Forest—are evaluated based on performance metrics (F-score, accuracy). The analysis reveals statistically significant links between sentiment trends and socio-cultural events, identified through keyword clustering. Beyond theoretical contributions, this framework provides practical applications:
Academic researchers can measure publication impact.
Content creators can gauge audience engagement in digital video platforms.
The proposed system improves upon prior work by enhancing real-world adaptability across diverse linguistic styles in user-generated social media content.},
        keywords = {Sentiment Analysis (Positive, Negative, Neutral), Social Media Analytics},
        month = {May},
        }