June 26 (UPI) — Scientists in Wales have designed a Twitter-monitoring algorithm capable of identifying riots before citizens report the unrest to police.
Researchers tested their model using social media data from the 2011 riots in London. Their predictive algorithm was able to identify specific instances of vandalism and violence before they were reported to police.
The model also identified places where youth were likely to gather. In most instances, the algorithm was able to identify criminal situations several minutes before police were made aware of the incidents. The model identified a handful of incidents more than an hour before they were reported.
“We have previously used machine-learning and natural language processing on Twitter data to better understand online deviance, such as the spread of antagonistic narratives and cyber hate,” Pete Burnap, a computer scientist at Cardiff University, said in a news release. “In this research we show that online social media are becoming the go-to place to report observations of everyday occurrences — including social disorder and terrestrial criminal activity.”
In 2011, anger over the shooting of a young man by police inspired groups of young people in Tottenham to riot. The seemingly isolated incidence quickly spread throughout London, leading to looting, vandalism and violence on a large scale.
Researchers developed their model by analyzing more than 1.6 million tweets related to the 2011 riots. They shared the results last month in the journal ACM Transactions on Internet Technology.
“Coming from a policing background myself I see the need for this type of cutting edge research every day. I wanted to develop a thesis that could have a real impact in real-world policing,” Cardiff researcher Nasser Alsaedi said. “I would like to see this implemented alongside the established decision-making processes.”
