At Face Value
Analysis of emotion based on facial imagery traces back to research conducted in the 1970s by Dr. Paul Ekman, who believed facial expressions betray emotions that run counter to people's words.
The psychologist developed a catalog of more than 5,000 micro-expressions, tiny muscular movements in the face that, he contended, signal feelings universally across human cultures.
Cicon, building on Ekman's work, used the software to analyze the faces of Fortune 500 executives for signs of fear, anger, disgust, and surprise. He found that the motions correlated with profit margins, returns on assets, stock price moves, and other measures of performance at the companies.
The software scanned videos of more than 200 CEOs and former CEOs of companies including Citigroup Inc., ConAgra Foods Inc., FedEx Corp., and Macy's. The videos included media interviews and footage shot during quarterly earnings calls.
Cicon and his team found that negative emotions, such as fear, anger, and disgust correlated positively with financial performance. CEOs whose faces during a media interview showed disgust were associated with a 9.3% boost in overall profits in the following quarter. CEOs who expressed fear saw their companies' stock rise .4% in the following week.
Cicon pointed to psychological research to explain why these negative emotions were a sign of positive movement in share price. “Fear is widely recognized as a powerful motivator. Thus it is not surprising to find that a CEO who appears fearful under interrogation is perceived by the market as a CEO who will work harder to increase firm value," explains Cicon.
Future of Facial Recognition
The results of Cicon's study could be of interest to investors, analysts, and journalists. In hopes of expanding on the study, Cicon plants to eventually teach the software to measure degrees of sincerity and truthfulness. The implications of this technology go beyond financial meetings. Such technology could have a future in criminal justice or in certain therapies.
There are certain concerns associated with the software, though. Accuracy has been an issue from the beginning, but it hasn't been tested independently as of yet. There are also concerns that a tool like this could run the risk of misuse. A misinterpreted emotion on a CEO's face, for instance, might contribute to market swings that cause a company to lose or gain value based on inaccurate information.
Cicon's results will be published in the Journal of Behavioral Finance in a forthcoming paper.