Pheme: The Social Media Lie Detector

 

Ever wondered if what you read online was real or fake? Or if a post you saw was fact or fiction?

Researchers are now working on creating an online lie detector called Pheme, which will scan through different posts, tweets, and comments to see if they are truthful. Named after a Greek character known for spreading rumours, this program will be able to sift through text found on Twitter, Facebook, and healthcare forums to tell the difference between truth and lie.

This project was initiated after further investigation of the 2011 London riots, in which people used Twitter in order to organize an uproar, as well as expose and spread false information. Pheme could have been extremely helpful in a situation like that.

At one point, there was even talk of shutting down social networking sites in order to prevent similar crises from happening.

"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," said Dr. Kalina Bontcheva, lead researcher on the project at the University of Sheffield.

The Pheme system would sift through information in real time and verify it to determine what is authentic. "It would trawl through the history and background of users to pinpoint accounts that were created purely to spread lies and rumours," said a report on Daily Mail.

Can we trust the internet? For the most part, I think yes. Can we trust online posts and comments made by other people? Not necessarily. The project's first results should be ready in eighteen months so it will definitely be interesting to see what happens. But imagine how cool it would be to automatically know if what you saw online was true or false? I guess we'll just have to wait and see.


For the full article, check out http://www.bbc.co.uk/news/technology-26263510.