Social media platforms can help predict disruptive events faster than police: study

By running an algorithm over 1.6 million tweets related to the London riots that took place in 2011, researchers from Cadriff University have concluded that Twitter, and other social media platforms, can be used to predict any disruptive event before they are reported to police.

In their research analyses the team found that by scanning tweets alone could have detected trouble in Enfield an hour and 23 minutes before the police were alerted about it. They say the real-time data, including location, time of incident, content, available at these social media platforms acts as “social sensors” to report any incident. “Automatically detecting and categorizing events, particularly small-scale incidents, using streamed data is a non-trivial task but would be of high value to public safety organisations such as local police, who need to respond accordingly,” the team said.

However, they still believe that such system can never replace the traditional policing systems used to find dangerous incidents. According to them, the scanning social media posts can be useful to detect large-scale incidents, but not minor ones.

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

“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.”