Detecting Gang-Involved Escalation on Social Media Using Context

TL;DR

This paper introduces a novel system that leverages domain-specific resources and contextual neural representations to detect aggression and loss in social media posts by gang-involved youth, aiming to predict potential violence.

Contribution

The paper presents a new approach combining domain-specific resources and contextual CNNs for detecting aggression and loss in social media, improving prediction accuracy.

Findings

Contextual CNN improves detection accuracy significantly.

Domain-specific resources enhance system performance.

System effectively identifies emotional and semantic cues related to violence.

Abstract

Gang-involved youth in cities such as Chicago have increasingly turned to social media to post about their experiences and intents online. In some situations, when they experience the loss of a loved one, their online expression of emotion may evolve into aggression towards rival gangs and ultimately into real-world violence. In this paper, we present a novel system for detecting Aggression and Loss in social media. Our system features the use of domain-specific resources automatically derived from a large unlabeled corpus, and contextual representations of the emotional and semantic content of the user's recent tweets as well as their interactions with other users. Incorporating context in our Convolutional Neural Network (CNN) leads to a significant improvement.