Twitter Inc (NYSE:TWTR) is better and faster than police at predicting a riot, according to a report from Cardiff University via Mashable.

Researchers analyzed 1.6 million tweets from the London 2011 riots and used machine learning algorithms to detect threats up to an hour faster than police.

They were able to create algorithms that scan Twitters and use various features of the micro-blogging site to identify threats. The researchers’ system analyzed things like the location of the tweet, the frequency of tweets containing certain words, and timing of the tweets.

In their report, researchers presented an integrated framework for detecting real-world events, both large and small, using Twitter Inc (NYSE:TWTR).

Using Twitter’s data and machine learning algorithms, researchers were able to detect trouble in Enfield an hour and 23 minutes before police were alerted to it, according to a report from The Independent.

Using machine learning technologies, posts on social media sites can be scanned to detect dangerous situations. People are increasingly using social media sites – Twitter, Facebook, Instagram, and Snapchat – to report incidents.

“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,” Dr. Pete Burnap, who is the study’s co-author, said in a statement.

However, researchers made is clear that no system can replace traditional policing systems. They said that the system that they developed using Twitter’s data and machine learning algorithms could be used to detect large-scale disorder rather than minor incidents.

“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,” Burnap added.