Boffins: You'll see, TWITTERNET! We'll get the TRUTH out of you...
Researchers try to build lie detector for social networks
While even emergency services have embraced Twitter as a way of conveying information to people quickly, the premature obituaries and malicious rumours seen on the social network every week show that you cannot trust what others tweet.
That's why computer boffins from five European universities have started work on a lie detector for social networks to try to sort the important information from the swathes of mindless dross.
“There was a suggestion after the 2011 riots that social networks should have been shut down, to prevent the rioters using them to organise," said lead researcher Dr Kalina Bontcheva from the University of Sheffield's Computer Science department. "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.
"This makes it difficult to respond to rumours, for example, for the emergency services to quash a lie in order to keep a situation calm. Our system aims to help with that, by tracking and verifying information in real time.”
The EU-funded project wants to separate out information into four types: speculation (such as whether interest rates might rise), controversy; misinformation, where people are repeating a lie unwittingly; and disinformation, where malicious rumours are spread on purpose.
To attempt this, the system will figure out how much authority the source has, such as a news outlet versus a member of the public, and look into the background of the account to ensure it hasn't been created specifically to spread false information.
The system will also look for other sources that confirm or deny the story and plot how the conversation has evolved to try to figure out if it's true or not. The assessment will be available to system users in a dashboard so they can see whether a rumour is taking hold.
“We can already handle many of the challenges involved, such as the sheer volume of information in social networks, the speed at which it appears and the variety of forms, from tweets, to videos, pictures and blog posts," Bontcheva said. "But it’s currently not possible to automatically analyse, in real time, whether a piece of information is true or false and this is what we’ve now set out to achieve.”
The three-year project, named Pheme after the personification of fame in Greek mythology, will be tested by journalists from the Swiss Broadcasting Corporation and by member of the Institute of Psychiatry at King's College London, who will be looking at recreational drug trends.
Sheffield and King's College will be collaborating with three other universities – Coventry's Warwick university and Germany's Saarland and MODUL University Vienna – and four firms – ATOS in Spain, iHub in Kenya, Ontotext in Bulgaria and the Swiss Broadcasting Corp. ®