A Machine That Can Tell When You're Lying

Washington: Computer scientists, taking inspiration from the human face, are exploring whether machines can detect lies.

In a study of 40 videotaped conversations, an automated system that analyzed eye movements correctly identified whether subjects were lying or telling the truth 82.5 percent of the time.

That's a better accuracy rate than expert human interrogators typically achieve in lie-detection experiments, said Ifeoma Nwogu, research assistant professor at University of Buffalo's Centre for Unified Biometrics and Sensors (CUBS) who helped develop the system.

"What we wanted to understand was whether there are signal changes emitted by people when they are lying, and can machines detect them? The answer was yes, and yes," said Nwogu, according to a Buffalo statement.

The automated system tracked a different trait - eye movement. The system employed a statistical technique to model how people moved their eyes in two distinct situations: during regular conversation, and while fielding a question designed to prompt a lie.

Nwogu's colleagues included CUBS scientists Nisha Bhaskaran and Venu Govindaraju, and Buffalo communication professor Mark G. Frank, behavioural scientist whose primary area of research has been facial expressions and deception.

People whose pattern of eye movements changed between the first and second scenario were assumed to be lying, while those who maintained consistent eye movement were assumed to be telling the truth.

In other words, when the critical question was asked, a strong deviation from normal eye movement patterns suggested a lie.

The research was presented as part of the 2011 IEEE Conference on Automatic Face and Gesture Recognition.