Cross-Platform Violence Detection on Social Media: A Dataset and Analysis

TL;DR

This paper introduces a new cross-platform dataset of violent social media posts and demonstrates that machine learning models can effectively detect violence across different platforms, aiding content moderation.

Contribution

The paper provides a novel, hand-coded dataset of 30,000 violent posts across platforms and shows cross-platform violence detection is feasible with high accuracy.

Findings

High classification accuracy across platforms

Effective training on one dataset and testing on another

Implications for content moderation strategies

Abstract

Violent threats remain a significant problem across social media platforms. Useful, high-quality data facilitates research into the understanding and detection of malicious content, including violence. In this paper, we introduce a cross-platform dataset of 30,000 posts hand-coded for violent threats and sub-types of violence, including political and sexual violence. To evaluate the signal present in this dataset, we perform a machine learning analysis with an existing dataset of violent comments from YouTube. We find that, despite originating from different platforms and using different coding criteria, we achieve high classification accuracy both by training on one dataset and testing on the other, and in a merged dataset condition. These results have implications for content-classification strategies and for understanding violent content across social media.