Twitter can detect riots quicker than police

Results show that the algorithms could have detected 2011 London riots an hour and 23 minutes before police

A new study by Cardiff University has determined that Twitter can be used to identify dangerous situations up to an hour faster than police reports.

Using the help of Twitter, researchers from Cardiff University used algorithms to analyse 1.6 million tweets from the London riots in 2011. Results showed that by scanning Twitter, the algorithms could have detected trouble in Enfield in 2011, which escalated to full fledge riots, an hour and 23 minutes before police were alerted.

The system noted the location the tweets were posted from and cross-checked it with the time they were posted along with its content. This data could help authorities quickly be routed to locations where events were going on and possibly prevent more from erupting.



The report maintains that social media sites can be used as a pool for reported incidents as users take to social media to report any kind of incident.

“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,” according to Pete Burnap, a co-author of the study.

However, the researchers made it clear that such systems are more suited to detect large-scale scattered incidents rather than minor incidents, and can 'never' be used to as an alternate to traditional policing systems. “We will never replace traditional policing resource on the ground but we have demonstrated that this research could augment existing intelligence gathering and draw on new technologies to support more established policing methods.”



Currently, police in Durham are using an artificial intelligence system called the Harm Assessment Risk Tool to determine whether a suspect should be kept in custody or released on bail.

This article originally appeared on The Independent