Lie Detector for Tweets? Researchers Working on It

'Pheme' aims to weed out deception online
By John Johnson,  Newser Staff
Posted Feb 19, 2014 7:40 PM CST
Updated Feb 19, 2014 8:00 PM CST
Lie Detector for Tweets? Researchers Working on It
   (Shutterstock)

European researchers say they're developing a system that can sniff out lies on Twitter, Facebook, and all manner of social media, reports the BBC. The goal of Pheme is to keep false rumors from gaining traction, and researchers say they can do so by analyzing where the tweets and posts come from, assessing their honesty, and reporting results back to users in real time, reports the Telegraph. The initiative is funded by the European Union and grew out of a spate of posts that spread false information during the 2011 London riots.

Forget Photoshopped photos, though. "We will not be doing image analysis, so we won't be looking to see if a photo has been altered—it's too technically difficult," says one of the researchers from the University of Sheffield. Pheme is expected to be ready for testing in about 18 months, and journalists will get the first crack at it. The false tweets will get lumped into four categories, notes the Daily Mail: speculation, controversy, misinformation, and disinformation, with only the latter involving deliberate lies. (More lie detector test stories.)

Get the news faster.
Tap to install our app.
X
Install the Newser News app
in two easy steps:
1. Tap in your navigation bar.
2. Tap to Add to Home Screen.

X