, claim their video-analysis software can analyze eye movement successfully to identify whether or not a subject is fibbing 82.5 percent of the time.)
THE EYES HAVE IT?: Researchers at the University at Buffalo, The State University of New York (U.B.), claim their video-analysis software can analyze eye movement successfully to identify whether or not a subject is fibbing 82.5 percent of the time.
Image: Courtesy of selimaksan, via iStockphoto.com
-
The Best Science Writing Online 2012
Showcasing more than fifty of the most provocative, original, and significant online essays from 2011, The Best Science Writing Online 2012 will change the way...
Read More »
A popular school of thought, dramatized in the recent TV drama Lie to Me, is that a careful study of facial expressions—especially eye movements—tells investigators if a perp is dissembling. Reality is neither as dramatic nor as decisive. Even experienced investigators average only about a 65 percent success rate, according to researchers. Could computers do a better job?
Researchers at the University at Buffalo, The State University of New York (U.B.), claim their video-analysis software can analyze eye movement successfully to identify whether or not a subject is fibbing 82.5 percent of the time. The researchers, who first presented their (still unpublished) results at the 2011 IEEE International Conference on Automatic Face and Gesture Recognition a year ago, believe they have laid the foundation for a more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 40 interviews were conducted by Mark Frank, a U.B. professor of communication and a study co-author, and included a diversity in age, gender and ethnicity. Prior to the interview, each subject was given the opportunity to "steal" a check made out to a political party or cause that the volunteer strongly opposed. Afterward, subjects sat down with a retired law-enforcement interrogator. The interviewer first posed conversational questions unrelated to the possible theft, to establish a baseline of normal eye movement, and then asked whether the interviewee had taken the check.
Those subjects who successfully lied received a monetary reward for themselves as well as for a group they supported. Those caught lying received nothing and were told that money would instead go to the party or group they opposed. The software compared each subject's baseline eye movement with those observed during the questions about the check. If the computer detected a large deviation, the researchers noted this change and flagged that person as a potential liar.
The work of Paul Ekman, professor emeritus of psychology at the University of California, San Francisco, School of Medicine served as an inspiration for the study. Ekman's specialty is the study of emotions and their relation to facial expressions, and his work formed the basis of the techniques used by fictional psychologist Cal Lightman in Lie to Me. Frank performed postdoctoral research at U.C. San Francisco's psychiatry department under Ekman's guidance.
Ekman's focus on brief, involuntary facial expression is not without critics. One former FBI special agent finds a fundamental flaw with the Buffalo study: "One problem with this research is its overreliance on the face as the only place to evince information from the body," says retired FBI counterintelligence special agent Joe Navarro, who spent 25 years with the bureau and was a founding member of its Behavioral Analysis Unit. "I can tell you as an investigator and somebody who's studied this not just superficially but in depth, you have to observe the whole body; it can't just be the face," he says, adding that a failure to take body language into consideration could lead to "an inordinate amount of false positives."
In future work, the Buffalo researchers plan to take a more holistic view of behavioral cues. "We know that the eyes give signals that lead to deception, but what about general body movements?" says Ifeoma Nwogu, study co-author and a research assistant professor in U.B.'s Center for Unified Biometrics and Sensors. Faster algorithms would also enable the software to flag behavioral deviations in near real-time, she adds. They also want to expand the sample size; the 40-person study is too small to be statistically significant.
An interview's setting or its context can also be important, Navarro says. "I did thousands of interviews with the FBI and most of them aren't in a laboratory, most of them aren't in a clean, sterile environment," such as the one in the Buffalo study, he says. "We did our own study years ago, and about 97 percent of interviews are actually done on the street, in the dark, after hours." These factors affect the interview subject's behavior and have an impact on whether an investigator can even clearly see a suspect's eyes.
Ultimately, the best law enforcement can do today is make a judgment based on their observations and experience, taking into account that interrogations can make even honest people a little anxious.
See what we're tweeting about
17 Comments
Add Comment"Those subjects who successfully lied received a monetary reward for themselves as well as for a group they supported. Those caught lying received nothing and were told that money would instead go to the party or group they opposed."
Reply | Report Abuse | Link to thisDoes anyone find something ethically wrong with this statement?
I think Buffalo has been watching too many fictional TV shows. Lies are like finger prints, no two are the same and no two people act the same. Even the most honest person, when stressed out by the presence on a police officer accusing you of a crime in an interrogation will give you a false positive. In every crime, there is positive evidence that the crime has been committed. If you cannot find the evidence and pin it to the person, then you must not arrest or convict, and circumstantial evidence is not evidence to convict or arrest. That is why a lie detector is an unreliable source of evidence in a court of law.
Reply | Report Abuse | Link to thisWhen Buffalo asked the test subject, "Did you take the check?" Somewhere in that persons life, they may had taken a check and their mind will relate that check to the present check and you will get a false positive. A well trained alert investigator would not need an algorithm to catch a perp, and if they do, the odds are excellent that you will be arresting an innocent person.
Has someone been watching "Blade Runner" lately??
Reply | Report Abuse | Link to thisThey lied; trust me, just look into my eyes.
Reply | Report Abuse | Link to thisVery interesting research. This would be a useful tool for law enforcement officers.
Reply | Report Abuse | Link to thisNothing , well, one of the biggest peeves I have is when I tell the truth and my Doc doesn't believe me abut pain or telling a story to people and they simply think because they have not experience it it is too far fetched ... my blood boils. I totally disagree with all of the textbooks on eye movement, and even body language. Because someone with severe scoliosis like me is always , always in some degree of pain, and discomfort, and maybe I am constipated? if so, the interview results are off. False +
Reply | Report Abuse | Link to thisReminds me of the Da Vinci Code, the scene where Langdon is closed in to an elevator with Captain Fasche as they descend to the murder scene. Noting Langdon's extreme discomfort and not recognizing it as claustrophobia, Fasche says "Is something wrong?" with a look on his face expressing suspicion. Not knowing Langdon's state of mind, Fasche is taking his extreme discomfort as they approach the crime scene as guilt and fear of getting caught.
Reply | Report Abuse | Link to thisI look forward to the freely distributed, 92% accurate app and the restructuring of governmental, economic, social and familial bonds among those who are still standing at the end of the process.
Reply | Report Abuse | Link to thisAt one time some retailers got the bright idea of using pre employment polygraph tests as a selection tool for future store clerks. I heard through the grapevine that those retailers had a tremendous amount of internal theft by employees. I met a number of the employees. They reminded me of those in a mental institution carrying the diagnosis of sociopathic personality disorder that I had worked with in a college course. Those retailers all went bankrupt.
Reply | Report Abuse | Link to thisI decided that if I ever became a big retailer, I would use a polygraph and hire those who failed it.
I hope this new technique works better.
Much to my discomfort, I knew an inveterate liar. He lied about *everything* even when the truth would have made him look better. He had a Master's in Psychology.
Reply | Report Abuse | Link to thisHe was a high school councilor. I was glad I had no children in his district.
It depends surely on the nature of the lie.
Reply | Report Abuse | Link to thisIf you asked Albert Einstein " do you understand Quantum Mechanics?", would he be lying or being truthful if he said no?
If I said yes, but Einstein said no, am I necessarily lying?
Many people say that when they passed their driving test they drove worse than when they failed! With greater understanding we may have more doubts. To interpret that as a truth/falsehood problem seems to me to create lots of lines of questioning that could create a response that looks like a lie . Barristers are skilled at it.
If under questioning X is asked Did you kill Y and answers " I don't know" and it looks like the truth, what responses are legitimate for the questioner?
If a person is asked the same question 4 times can 2 answers look true and 2 false even if same answer is given?
Thanks for the article, it made me think..(truth?)
Kinda reminds me of the years I was in high school. Was on my way home from the public library with a book on PYROTECHNICS in my possession, hitch-hiking. They
Reply | Report Abuse | Link to thisbooked me on the charge of "soliciting rides" at a suburban precinct station but, during the night, transferred me to the down town main police station where I was booked on the charge of "arrest for investigation of arson". They interrogated me about
local incidents involving arson to which I laughed about
being arrested for possessing a library book regardless of its title or subject. They interpreted laughter as
an indicator of a lie and put me in a line up and in the same cell occupied by a robber, a murderer, and a pedophile. After taking a polygraph test, I was out on the street in ten minutes. And I was a high school kid with a mere library book. I have been denied equal opportunity ever since.
A person who is truly amoral would pass because they feel no guilt.
Reply | Report Abuse | Link to thisIt would be interesting to test their video-analysis software during the debates for the current Republican Presidential candidates.
Reply | Report Abuse | Link to thisWonder what the results would give?
Reply | Report Abuse | Link to thisSeveral things come to mind. First, can lies be detected if the person telling the lie does not know he/she is lying? This leads to me wondering why the investigator assumes that if a person is lying it will somehow be revealed unintentionally. But isn't lying supposed to be an intentional act? Are there "subconscious" forces acting unbeknownst to the liar? If so, how do you prove that such forces exist without being circular? And would these unconscious forces be acting even if someone didn't know he/she was telling a lie? Finally have any professional liars been subject to this investigators methods?
That is a great idea, running this software on digital recordings of the presidential debates, for both candidates. The beauty is this could be done in the privacy of one's own home, if of course, one had the software on their laptop. That would be a great tool in making a decision on which candidate is truly honest.
Reply | Report Abuse | Link to thisThe problem here, however, is what one commenter suggested about truly amoral individuals passing the test. If a candidate was such, they would pass with flying colors.
Come to think of it, I'm willing to bet the CIA is running black ops video analysis software on the candidates that dwarfs this publicly known software in capabilities, perhaps costing billions and years ahead of the capabilities described in this article. They may already know who is a danger to this country and act accordingly.
i understand what you are trying to say, but it is not logical...if you cannot find out who is is telling a lie and who is not, then how on earth can you search for the evidence to convict the person?
Reply | Report Abuse | Link to this