Academics create algorithm that can detect if you're lying in emails

A lie has no legs, the saying goes, but when you’re online, you don’t need legs. You can cruise through the Internet, lying to people free of the little signals which could give you away, such as body language.

This is a topic academics from the Cass Business School tackled, ultimately creating an algorithm that can detect lies in an email. I’m totally serious.

It works by detecting "linguistic cues of deception". The paper, "Untangling a Web of Lies: Exploring Automated Detection of Deception in Computer-Mediated Communication" will be published in Journal of Management Information Systems.

For example, liars tend not to use personal pronouns and superfluous descriptions such as unnecessary adjectives, and over-structure their arguments. They minimize self-deprecation, but will include extra flattery, as they want to make themselves extra likeable.

Cass Business School says the practical implications are "wide-ranging", especially for businesses relying on email for communication.

"This research opens up the possibility of fraud prevention and deception detection technology across lots of in-person domains, not just e-mail", said Dr Tom van Laer, senior lecturer in Marketing at Cass Business School. "Our approach comes from big data -- combining statistics with natural language processing patterns that tip us off to deception. Authorities and companies will now be able to figure out the plausibility of fraud and identify lying individuals".

Sadly, there is still no app to help us virtually punch people in the face through the monitor for lying, but just knowing who not to trust is good enough.

Published under license from ITProPortal.com, a Net Communities Ltd Publication. All rights reserved.

Photo Credit: Shutterstock/luckyraccoon