People Smile When Frustrated: Researchers Develop Computer Algorithm to Detect Fake Smile (Video)
When you see a person smile, you are more likely to interpret that the person is happy or delighted. Obviously, conventional understanding of expressions tells us that when a person is happy, he/she smiles. Yet, a new study has revealed that people smile even out of frustration. Most people might not think so, but they do.
Researchers at MIT have not only found that people smile when frustrated, perhaps to cope with the frustration, they have also developed a computer system which can tell a genuine smile from a smile that is a result of frustration with more accuracy than human beings.
The idea behind developing such a program that could identify emotional states or expressions is to help and train those who have difficulty interpreting expressions. Such as, people with autism.
"The goal is to help people with face-to-face communication," says Ehsan Hoque, a graduate student in the Affective Computing Group of MIT's Media Lab who is lead author of a paper just published in the IEEE Transactions on Affective Computing. Hoque's co-authors are Rosalind Picard, a professor of media arts and sciences, and Media Lab graduate student Daniel McDuff.
For the study, a sample group of people were brought in to the lab, and given long and tedious online forms to fill out, while being recorded. The form was intentionally designed to be irritating and frustrating, and regardless of what the participants typed, as soon as they pressed the 'submit' button, the form cleared on its own and went back to the beginning.
The researchers were surprised to see that a lot of people who were frustrated smiled for a while "to cope up with that environment," says Hoque.
According to MIT's official Web Site, when participants were asked to act as if they were frustrated, 90% of them did not smile. However, when genuinely frustrated, 90 percent of them did smile. Although there is not much difference between a delighted and a frustrated smile, the analysis of a video of participants revealed that the two kinds of smiles were quite different: While the happy smiles progressed gradually, the frustrated smiles appeared and disappeared quickly.
To understand the subtleties and underlying emotions of expressions is a major goal of this research, Hoque says. "People with autism are taught that a smile means someone is happy," he says, however, research shows that it is not as simple as that.
During the research, Hoque says, human beings were found to be able to detect a delighted smile more accurately than the computer algorithms. However, a frustrated smile was more accurately detected by the computer. The possible explanation given by him for phenomenon is that human beings zoom out and interpret an expression, whereas computer algorithm can utilize the minute details of the signal which is much more unwitting.
Jeffrey Cohn, a professor of psychology at the University of Pittsburgh says this work "breaks new ground with its focus on frustration, a fundamental human experience. While pain researchers have identified smiling in the context of expressions of pain, the MIT group may be the first to implicate smiles in expressions of negative emotion."
The research, apart from training autistic people might also be useful for marketers. The conventional perception of relating smile to happiness can be broken. "Just because a customer is smiling, that doesn't necessarily mean they're satisfied," Hoque says.
Media Lab consortium sponsors and Procter & Gamble Co supported the study.