AI Could Be Used To Help Predict When Protests Might Turn Violent

Protests can be useful to help bring attention to a certain topic, but sometimes protests can turn violent which is unfortunate, which is why police are usually deployed to monitor protests and to help keep the peace. However whether or not a protest has a chance of turning violent is anyone’s guess, but that might soon no longer be guess work.

Researchers at USC have created an algorithm (via Digital Trends) that scans social media and predicts if an ongoing protest has the potential to become violent. This is done by analyzing the language used on social media platforms, such as Twitter, to indicate if protesters are starting to get worked up and if they might be frustrated enough to resort to violence to get their message across.

Speaking to Digital Trends, Joe Hoover, a USC PhD student who led the study said, “By tracking moralized tweets posted during the 2015 Baltimore protests, we were able to observe that not only did their volume increase on days with violent protests, but also that their volume predicted hourly arrest rates, which we used as a proxy for violence, during the protests. To further unpack these effects, we conducted a series of controlled behavioral experiments and we consistently observed the same effect of moral convergence.”

He adds, “Protests that exhibit high convergence should be handled carefully, as even a small spark of conflict could lead to violence. Perhaps monitoring convergence on an issue could help emergency services devise and implement strategies for promoting peaceful protest.”

Tyler Lee
Categories: General
Tags: AI (Artificial Intelligence), _cold