• by Erik Sass , Staff Writer @eriksass1, February 19, 2014

Social media is a great channel for disseminating information, which also means it’s a great channel for spreading disinformation. While it won’t tell you if your online acquaintances are as fake as you suspect, it might help prevent riots.

To combat the spread of lies online, researchers at Britain’s University of Sheffield are working on a social media lie detector.
 
The researchers set out to create an algorithm that can automatically analyze, in real time, pieces of information to determine whether they are true or false. The development team said this could allow journalists, governments, emergency services, health agencies and the private sector to respond more effectively to claims on social media, especially in emergency situations, such as civil disorder and epidemics, important events like elections.
 
One example cited by the researchers was the 2011 riots in London, when a variety of false information circulated online, including one terrifying rumor that all the animals from the London Zoo had been set free to roam the streets.
 
Lead researcher Dr. Kalina Bontcheva, from the University of Sheffield’s department of computer science, explained: “There was a suggestion after the 2011 riots that social networks should have been shut down, to prevent the rioters using them to organize. 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 rumors, 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,” he added.
 
The projects sorts online rumors into four types: speculation, for example whether interest rates might rise; controversy, as over the alleged ill effects of vaccines; misinformation, where erroneous information is spread by mistake; and disinformation, in which it’s done deliberately, with malicious intent.

The system will automatically categorize sources to assess their authority, including news outlets, journalists, experts, supposed eyewitnesses, members of the public and automated ‘bots’. Its algorithm will then look for history and background, to determine whether Twitter accounts have been created purely to spread false information. Then, it tries to find corroborating (or contradictory) information and analyze the structure of online conversations over social networks, to reach a final determination about truth or falsehood.