Study finds indirect aggression peaks in Indian X conversations during major events

A machine learning study examining over 131,000 posts on X has revealed patterns of aggressive communication among Indian social media users, with indirect aggression emerging as the most common form during emotionally charged moments. The research, conducted by scientists at Goa Institute of Management and Goa Business School, employed advanced algorithms to classify posts into three distinct categories: Overtly Aggressive, Covertly Aggressive, and Non-Aggressive communication. The findings, published in the peer-reviewed journal Advances in Consumer Research, provide fresh insights into how Indians express hostility online across different contexts.

The study titled "Indian Aggression Detection through Multiple ML Models from Twitter Data" focused on understanding whether machine learning could effectively identify varying forms of aggression in Indian social media discourse. Researchers found that the intensity and nature of aggressive responses fluctuated significantly depending on the type of event triggering online discussions. Major social, financial, sporting and political events proved to be key catalysts for increased hostile commentary, with indirect or covert aggression becoming the preferred mode of expression rather than overt hostility.

The research underscores the growing importance of understanding digital communication patterns in India's increasingly connected population. As social media platforms continue to shape public discourse, the ability to detect and categorize different forms of aggression could help platforms develop more nuanced moderation strategies and provide researchers with tools to monitor online behaviour during sensitive periods.