For the first time ever scientists are able to read a person's mind by indentifying emotions through brain scans.
The study showed how the brain categorizes feelings, allowing researchers to identify emotions on the scan, according to a Carnegie Mellon press release. In the past, research on emotions has been difficult because people were reluctant to accurately report their feelings.
The team remedied this obstacle by using actors, who regularly cycle through emotions, for the study.
"We were fortunate, in that respect, that CMU has a superb drama school," said George Lowenstein a Herbert A. Simon University Professor of Economics and Psychology. He described the method as their "big breakthrough."
The researchers combined "functional magnetic resonance imaging (fMRI) and machine learning" to measure the brain signals of the 10 actors. The actors were instructed to enter the emotional state of each of these emotions: "anger, disgust, envy, fear, happiness, lust, pride, sadness and shame," in random orders.
The team also presented the subjects with both disgusting and neutral photos; the brain scans were able to take the information gathered in the first part of the study and figure out the emotions elicited from the pictures.
Out of the nine emotions the computer model scanned in the first part of the study, it was able to tell when a participant was feeling disgust 60 percent of the time, 80 percent of the time the computer had disgust in it's top two guesses.
Without the prior tests the computer would be able to guess a subject's emotions at a rank accuracy of 0.50, here the computer achieved a rank accuracy of 0.71.
The scientists discovered the computer maintained accuracy even when the computer assessed brain patterns in only a few subsections of the brain.
"This suggests that emotion signatures aren't limited to specific brain regions, such as the amygdala, but produce characteristic patterns throughout a number of brain regions," said Vladimir Cherkassky, senior research programmer in the psychology department.
The program proved to be most accurate when predicting happiness, but was able to identify envy least often. It rarely confused positive and negative emotions, leading researchers to believe they have distinctive patterns. Lust was rarely misidentified, so it may have it's own unique brain pattern.
"We found that three main organizing factors underpinned the emotion neural signatures, namely the positive or negative valence of the emotion, its intensity - mild or strong, and its sociality - involvement or non-involvement of another person," said Marcel Just, the D.O. Hebb University Professor of Psychology and director of the university's Center for Cognitive Brain Imaging. "This is how emotions are organized in the brain."
In the future the scientists hope to learn how to identify suppressed emotions, and feelings that are being experienced simultaneously.
WATCH:
