Twitter Lie Detector to Identify Hoax Tweets

A lie detector is being developed for Twitter by international scholars to remove false posts.

Universities across Europe will be working together to build a new system, called Pheme, to filter rumours from the facts.

During the 2011 London riots it highlighted the role social media played in the unrest when rumours circulated that animals at London Zoo had been set free.

It has also been used in world conflicts to spread dangerous and damaging rumours.

The University of Sheffield is leading the project with a group of international researchers whose aim is to classify online rumours into four categories: speculation, controversy, misinformation and disinformation.

It will also analyse history and background of those Twitter accounts, which have been created solely for the purpose of spreading false information.

Team leader Dr Kalina Bontcheva said: "There was a suggestion after the 2011 riots that social networks should have been shut down, to prevent the rioters using them to organise.

"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.

"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.

"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 system was named Pheme after a Greek mythology character who gossiped about the affairs of mortals and gods until everyone knew.