Fake Twitter rumours could be a thing of the past with a new system on the way that claims to be able to analyse, in real time, whether a post is real or not.
The social media lie detector, called Pheme, is the brainchild of researchers at the University of Sheffield and has been developed in order to assist organisations, such as the government and emergency services, so that events can be dealt with as quickly as possible.
"There was a suggestion after the 2011 riots that social networks should have been shut down, to prevent the rioters using them to organise," Dr Kalina Bontcheva, lead researcher on the project at the University of Sheffield, told the BBC. “But social networks also provide useful information. The problem is that it all happens so fast and we can't quickly sort truth from lies.”
Researchers started working on the project after analysing research based on the use of social media during civil unrest that broke out in London back in 2011.
Data analysed by the solution will include posts on Twitter as well as comments in healthcare forums and public comments on Facebook with researchers classing the rumours into four different groups – Speculation, Controversy, Misinformation and Disinformation.
Speculation covers comments such as whether interest rates will rise, controversy applies to content similar to that involved in the MMR vaccine scandal, misinformation covers untrue content spread unwittingly, and disinformation applies to the intentional spread of false information.
Only text will be analysed as part of the project and results of searches will be shown on a visual dashboard that will help to show if a rumour is taking hold and it’s hoped the first set of results will be produced in 18 months time.
In addition to Sheffield there are four other universities taking part, including Warwick, King’s College London, Saarland in Germany, and Modul in Vienna, as well as four companies – Atos, iHun, Ontotext, and swissinfo.
The project is set to run for three years and by the end it’s hoped that a personalised tool for journalists will be created to help news organisations in times of unrest.