We are becoming scarily close to AI when machines can accurately recognise human emotions.
Dr Luke Chang from the Department of Psychology & Neuroscience, University of Colorado and his team of researchers have found that negative human emotions have a ‘neural signature’ which a computer can learn and then can predict with 90% accuracy through reading brain scans.
How To Read Someone’s Emotions With 90% Accuracy
First reported by the excellent Psyblog (www.spring.org.uk) Dr Chang who led the study said:
“This means that brain imaging has the potential to accurately uncover how someone is feeling without knowing anything about them other than their brain activity.
This has enormous implications for improving our understanding of how emotions are generated and regulated, which have been notoriously difficult to define and measure.
In addition, these new types of neural measures may prove to be important in identifying when people are having abnormal emotional responses — for example, too much or too little — which might indicate broader issues with health and mental functioning.”
For the research, 182 people looked at photos designed to illicit a negative response. These included pictures of physical injuries, hate groups and acts of aggression. Using brain scans, a computer was able to learn the ‘neural signature’ of negative emotion.
Dr Chang said:
“We were particularly surprised by how well our pattern performed in predicting the magnitude and type of aversive experience.
As skepticism for neuroimaging grows based on over-sold and -interpreted findings and failures to replicate based on small sizes, many neuroscientists might be surprised by how well our signature performed.
Another surprising finding is that our emotion brain signature using lots of people performed better at predicting how a person was feeling than their own brain data.
There is an intuition that feelings are very idiosyncratic and vary across people.
However, because we trained the pattern using so many participants — for example, four to 10 times the standard fMRI experiment — we were able to uncover responses that generalized beyond the training sample to new participants remarkably well.”
The study was first published in the journal PLOS Biology (Chang et al., 2015) and then in Psyblog