Lie Detecting Algorithm

Researchers have developed an algorithm that can spot a liar in a text 70% of the time.

09:11 08 July 2016

A lie detecting algorithm has been developed to spot a liar in email and dating profiles. The algorithm, developed by Cass Business School, identifies linguistic cues of deception found within a computer-mediated communication (CMC) system.

 

The team found that those who are being deceitful:

 

·       Are less likely to use personal pronounces as they want to dissociate themselves from what is being shared

 

·       Use more adjectives and fill messages with unneeded words

 

·       Minimise self-deprecation and include more flattery so they would appear more accommodating and likeable

 

·       Pattern the linguistic style of the recipient across e-mail exchanges

 

·       Tend to write in the same structure as the person they are communicating with

 

 

'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.'