In a recent study by researchers at the University of Illinois, we had already been given clues about how the face could reveal political orientation : specifically, the ugliest people tend to be progressive, the most beautiful, conservative.
Now a study that has just been published goes further and, thanks to an algorithm, reaches a degree of precision when it comes to guessing whether the person is conservative or liberal that exceeds even that of long questionnaires .
Depending on our ideology, we will lean slightly more towards a more group empathy (caring for our own) and less general (caring as a symbol, even if that means caring less for ours). Both positions have their pros and cons .
What seems to contradict our intuition is that these political tendencies have a reflection on our face (which forces us to ask ourselves what was before, if the chicken or the egg: we vote this way because we have a certain face or we get a certain face because we vote like this .
The degree of success of this algorithm, be that as it may, is 72% .
The study used a facial recognition algorithm on images of 1,085,795 people to predict their political orientation by comparing their similarity to the faces of other liberals and conservatives. Political orientation was classified correctly in 72%, and the precision was similar in the United States, Canada and the United Kingdom, and in various settings (Facebook and dating websites).
The highest predictive power was provided by head orientation (58%), followed by emotional expression (57%). Liberals tended to look at the camera more directly, were more likely to express surprise, and less likely to express disgust. Facial hair and glasses predicted political orientation with minimal precision (51-52%).
In future studies, a more detailed analysis could be obtained by exploring the links between political orientation and facial features extracted from images taken in a standardized environment while monitoring facial hair, grooming, facial expression, and head orientation.
If you want to know more about this study and its implications, I’ll explain it to you in the following video: