International Journal of Scientific Research and Engineering Development

Social media generates a ton of real-time data that shows what people think, recent happenings, and things that are getting popular. Machines do a lot of the analyzing, but most methods aren't very helpful—they lookat opinions and trends in a static way that isn't all that useful. It lacks transparency, doesn't offer practical uses, and its evaluations aren't fair. This paper puts forward a new framework for dealing with Big Data Analytics focused on predicting social media trends. They include real-time processing, which is pretty cool, along with something called Explainable AI (XAI) and models for making decisions. Not only does this help predict whether a topic will go viral, it also rates how much influence we can realistically expect that topic to have, thanks to the Trend Actionability Index (TAI). SHAP techniques get used to figure out what the key elements are—like engagement rates, growth of hashtags, and the clout of influencers. From the tests, this method boosts transparency and early trend detection, while being good for digital marketing and public relations too. So yeah, keywords here are Big Data Analytics, Social Media Trends, Explainable AI, SHAP, Trend Prediction, and Viral Modeling, with a nod to Fairness in Machine Learning.

Ankit Baghel, Satish Gujar,"Big Data Analytics for Social Media Trends" International Journal of Scientific Research and Engineering Development, V9(3): Page(1862-1867) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.