A Computational Analysis of Polarization on Indian and Pakistani Social Media

TL;DR

This paper analyzes Twitter messages during the Pulwama attack and subsequent tensions, revealing that Indian BJP politicians used more polarized hashtags and called for escalation, highlighting social media's role in conflict escalation.

Contribution

It introduces a novel hashtag co-occurrence based label propagation method to identify polarizing tweets and politicians during international conflicts.

Findings

BJP politicians used more polarized hashtags.

Polarized messages increased during escalation.

Framework for studying social media polarization in conflicts.

Abstract

Between February 14, 2019 and March 4, 2019, a terrorist attack in Pulwama, Kashmir followed by retaliatory airstrikes led to rising tensions between India and Pakistan, two nuclear-armed countries. In this work, we examine polarizing messaging on Twitter during these events, particularly focusing on the positions of Indian and Pakistani politicians. We use a label propagation technique focused on hashtag co-occurrences to find polarizing tweets and users. Our analysis reveals that politicians in the ruling political party in India (BJP) used polarized hashtags and called for escalation of conflict more so than politicians from other parties. Our work offers the first analysis of how escalating tensions between India and Pakistan manifest on Twitter and provides a framework for studying polarizing messages.