Twitter system catches riots faster than police

Computers could detect riots in progress by scanning social media posts before police are made aware, research has found.

Jun 28, 2017

Computers could detect riots in progress by scanning social media posts before police are made aware, research has found. A study by Cardiff University saw computer systems use Twitter data from the 2011 riots to find out about shop break-ins and arson attacks up to an hour before they came to police attention. The system could also work out where riots were rumoured to take place and where young people were gathering. The experts believe their findings could help officers better manage and prepare for public disorder events. Report co-author Dr Pete Burnap said: “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. “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.” The researchers analysed 1.6 million tweets relating to the 2011 riots that spread across England after Mark Duggan was shot by the Metropolitan Police Service (MPS). Using machine-learning algorithms, they were able to detect disruptive events an average of several minutes faster than police sources in all but two cases. In regards to the rioting in Enfield, the system could have learned of the disorder an hour and 23 minutes before the MPS became aware. Dr Nasser Alsaedi said: “Coming from a policing background myself I see the need for this type of cutting edge research every day. “I would like to see this implemented alongside the established decision-making processes.”

Related News

Select Vacancies

Chief Inspector

Nottinghamshire Police

Promotion to Sergeant

Bedfordshire, Cambridgeshire and Hertfordshire Alliance

Copyright © 2021 Police Professional