Communications of the ACM
Carnegie Mellon Researchers Identify Emotions Based on Brain Activity
The average positions of brain regions used to identify emotional states.
Credit: Carnegie Mellon News (PA)
Carnegie Mellon University (CMU) researchers have developed a method to identify which emotion a person is experiencing based on brain activity. The method combines functional magnetic resonance imaging (fMRI) and machine learning to measure brain signals to accurately read emotions in individuals.
"This research introduces a new method with potential to identify emotions without relying on people's ability to self-report," says CMU professor Karim Kassam.
As part of the study, 10 actors were scanned while viewing the words of nine emotions. Inside the fMRI scanner, the actors were instructed to enter each of these emotional states multiple times, in random order. The second phase of the study presented the participants with pictures of neutral and disgusting photos, and after the computer model had learned the emotion patterns from self-induced emotions, it could correctly identify the emotional content of the photos being viewed using the brain activity of the viewers. The researchers then took the machine-learning analysis of the self-induced emotions to guess which emotion the subjects were experiencing when they were exposed to the disgusting photographs.
The research builds on previous work by CMU's Marcel Just and Tom M. Mitchell, which used similar techniques to create a computational model that identifies individuals' thoughts of concrete objects.
From Carnegie Mellon News (PA)
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found