Muscle reactions in the face reveal lies
A new technology detects lies based on minimal muscle reactions in the face. In the future, special cameras, for example in banks, at the airport or during police interrogations, could expose liars.
Tel-Aviv (Israel). In criminology, methods such as polygraphs and brain scans are used to identify lies and false statements. However, these methods can be deceived and even trained observers can therefore not always judge whether there is a lie. Scientists at Tel Aviv University have now discovered an alternative to conventional lie detectors.
According to their publication in the specialist magazine Brain and Behavior the method is based on subtle muscle reactions in the face that occur when lying. “According to the theory, a deception manifests itself through involuntary micro-facial expressions that only last 40 to 60 milliseconds, but do not match the emotions that the person wants to convey through their lie,” explain the scientists.
Impulses of the facial muscles
To detect these minimal twitches, the researchers working with Anastasia Shuster have developed small electrodes that are stuck to the face. These were tested in experiments in which two test subjects sat opposite each other. The people had headphones on, through which they were told a word. Then they should either tell their counterpart the word they heard or lie, i.e. name another word.
High accuracy of the lie detector
In about half of the cases, the test subjects were able to tell whether they had been lied to. The new lie detector, however, was able to use the muscle reactions of the forehead and cheek to detect in all 40 test subjects whether they were lying. “This is the first evidence of polygraph detection using surface EMG in such a situation,” explains Shuster.
Artificial intelligence recognizes lies
The scientists then trained an artificial intelligence (AI) to recognize certain muscle signals from the test subjects. “With this method we achieved a hit rate of 73 percent – not perfect, but still better than most of the technology that has existed to date,” explains Dino Levy. The authors suspect that people also unconsciously recognize the involuntary muscle reactions and thus judge whether the person opposite is lying.
“In our study, the lies were very simple. But when we lie in real life, we often tell longer stories that usually contain both true and false components, ”explains Levy. The scientists therefore want to investigate whether the muscle reactions are similar to complex lies. If this is the case, it will be easier to spot lies in the future.
Instead of electrodes, the muscle reactions could also be detected with high-resolution cameras. “Whether in the bank, during police interrogations or at the airport, cameras linked to an AI could then differentiate between truth and lies. As soon as our technology is perfected, the algorithms trained even better and the electrodes become superfluous, this method could find numerous applications, ”explains Levy.
Brain and Behavior, doi: 10.1002/brb3.2386