Om Venkatesh Sharma
Delhi Public School, Vasant Kunj
Download PDF
http://doi.org/10.37648/ijrst.v14i04.008
In today’s fast-paced digital landscape, short-form video content has emerged as a dominant mode of user engagement, particularly through platforms like Instagram Reels. As creators, marketers, and platforms seek to understand what makes content go viral, predictive analytics powered by large-scale data has become a compelling research frontier. This paper presents a machine-learning-based approach to predicting viral moments using metadata from 50 million publicly available Instagram Reels. We define virality using statistical thresholds on engagement metrics such as views, likes, shares, and comments, identifying the top 10% as "viral."
Disclaimer: Indexing of published papers is subject to the evaluation and acceptance criteria of the respective indexing agencies. While we strive to maintain high academic and editorial standards, International Journal of Research in Science and Technology does not guarantee the indexing of any published paper. Acceptance and inclusion in indexing databases are determined by the quality, originality, and relevance of the paper, and are at the sole discretion of the indexing bodies.
