Can computer software detect lies at a better rate than people? Scientific American reports that researchers at the University at Buffalo, The State University of New York claim that their software, which analyzes eye movement can determine a lie with 82.5% accuracy. Their work, which is as of yet unpublished, consisted of 40 interviews with subjects that were given a punishment/reward scenario. If they were to successfully lie and get away with it, they would be given a cash reward plus a group they support will be given a donation. If they were caught lying, a group they oppose were given money.
Obviously, a 40 subject study is hardly a thorough study but they have bigger plans for their research.
The researchers, who first presented their (still unpublished) results at the 2011 IEEE International Conference on Automatic Face and Gesture Recognition a year ago, believe they have laid the foundation for a more extensive study that will include a larger sample and take into account body language in addition to eye movement to determine whether new technologies can help interrogators in their search for the truth.
The study is based off of work of Paul Ekman, a Professor Emeritus psychology at the University of California, San Francisco, School of Medicine. Ekman studied emotions and their relation to facial expressions. The study’s co-author, Mark Frank, worked for Ekman U.C. San Francisco’s psychiatry department previously.