AI Case Study

University of Southern California researchers predict risk of violent protest with a Twitter-based model

Researchers at USC's Brain and Creativity Institute investigated whether they could correlate outbreaks of violent protest with social media activity. Perhaps unsurprisingly they could - but this is not yet a predictive tool as the data was all retrospective.

Industry

Public And Social Sector

Security

Project Overview

According to Engadget, researchers used machine learning to analyze "18 million tweets posted during Baltimore protests in 2015, which broke out after Freddie Gray fell into a coma on a police transport and later died. The team explored the association between arrest rates (a metric often used to signal violent incidents) and moral tweets (i.e. those related to issues the posters could deem as right or wrong). The number of arrests during the demonstrations correlated with the number of moral tweets posted in the hours leading up to a protest -- the number of tweets containing moral language almost doubled on days with violent clashes between police and protesters.
The researchers found that when people moralize the issue they're protesting, they're more likely to endorse violence. There's an echo chamber effect too -- a study published in Nature Human Behavior showed when some people were confident others in their social circle shared their moral views, the more likely they were to consider violent attacks on opponents."

Reported Results

Study offers the potential for building a predictive tool

Technology

Function

Risk

Security

Background

Researchers investigated whether they could correlate outbreaks of violent protest with social media activity.

Benefits

Data