Computers are more Skilled than People at Detecting Real Pain
Pain is a subjective emotion that can be hard to measure. Most of the time, pain is expressed via vocal and facial cues. However, these cues can be faked, especially by people with alternative motives, such as drug addicts who want higher dosages. In a new study, researchers examined whether or not people could detect fake pain as accurately as a computer system. The team from the University of California San Diego and the University of Toronto found that the computer system is more skilled than people at differentiating fake pain from real pain.
Senior author, Kang Lee, professor at the Dr. Eric Jackman Institute of Child Study at the University of Toronto, said, "In highly social species such as humans...faces have evolved to convey rich information, including expressions of emotion and pain. And, because of the way our brains are built, people can simulate emotions they're not actually experiencing - so successfully that they fool other people. The computer is much better at spotting the subtle differences between involuntary and voluntary facial movements."
In this study, the researchers calculated how accurate humans and the computer system were in detecting fake pain. They found that humans, even after they were trained to look for certain signs, only had an improved accuracy of 55 percent. The computer system, however, was able to detect pain 85 percent of the time.
"The computer system managed to detect distinctive dynamic features of facial expressions that people missed," said the study's lead author, Marian Bartlett according to Medical Xpress. "Human observers just aren't very good at telling real from faked expressions of pain."
The researchers hope that the computer system could reveal more information behind "emotional signaling." From this study, the team was able to identify the mouth as the best indicator of fake expressions. The researchers detailed that when people faked pain, their mouths were opened more frequently and with less variation.
"Further investigations will explore whether over-regularity is a general feature of fake expressions," the researchers stated.
The study, "Automatic Decoding of Deceptive Pain Expressions," was published in Current Biology.