acm-header
Sign In

Communications of the ACM

ACM TechNews

Eu Project to Build Lie Detector For Social Media


A man strapped to a polygraph ('lie detector').

An EU-funded project is aimed at classifying online rumors, to help sort the truth from the lies.

Credit: sf.funcheap.com

University of Sheffield researchers are leading a European Union-funded project to classify online rumors into four types: speculation, controversy, misinformation, and disinformation.

Although social networks can provide useful information, it can be difficult to sort out the truth from lies. "Our system aims to help with that, by tracking and verifying information in real time," says University of Sheffield researcher Kalina Bontcheva.

The new system will automatically categorize sources to assess their authority, such as news outlets, individual journalists, experts, potential eyewitnesses, members of the public, or automated bots. The system will also look for a history and background to try to determine where Twitter accounts have been created simply to spread false information. The results will be displayed to the user in a visual dashboard to allow them to see whether a rumor can be verified.

"It's currently not possible to automatically analyze, in real time, whether a piece of information is true or false and this is what we've now set out to achieve," Bontcheva says.

From University of Sheffield
View Full Article

 

Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA


 

No entries found