Is science reality starting to resemble science fiction? Recently, researchers from multiple universities wrote a paper in Frontiers in Human Neuroscience that purportedly showed how AI can predict people’s personalities by studying their eye movements.
The title is “Eye Movements During Everyday Behavior Predict Personality Traits.” The authors are Sabrina Hoppe, Tobias Loetscher, Stephanie Morey and Andreas Bulling. Their affiliations are University of Stuttgart, University of South Australia, Flinders University, and the Max Planck Institute for Informatics. Their fields of specialty range from robotics to psychology to perceptual user interfaces.
Here’s how the study was conducted. The researchers tracked the eye movements of 42 participants as they ran an errand on a university campus. They had to wear an off-the-shelf head-mounted eye tracker on their errands, according to Digital Trends.
The participants were instructed to walk around campus and to purchase any items of their choice such as a drink or confectionary from a campus shop of their choice. When the tracing was stopped, the glasses were removed. Participants were then asked to fill in the personality and curiosity questionnaires.
The AI was used to link the two correlating factors—eye movement data and personality trait types.
Results: Researchers were able to predict a number of traits as well as perceptual curiosity only from eye movements.
“People with similar traits tend to move their eyes in similar ways. For example, optimists spend less time looking at negative emotional stimuli, like images of cancer, while curious people tend to take in all regions of a scene,” commented Newsweek.
The technology involved (1) a machine learning method and (2) a set of features encoding different eye movement characteristics. “Thanks to the machine learning approach, we could automatically analyze a large set of eye movement characteristics and rank them by their importance for personality trait prediction,” noted the research team.
They added that the proposed machine learning approach is on the mark in predicting levels of agreeableness, conscientiousness, extraversion, and perceptual curiosity. “It therefore corroborates previous laboratory-based studies that have shown a link between personality traits and eye movement characteristics.”
Still the results, while a step in the right direction, are not conclusive
Authors admit that the predictions are not yet accurate enough for practical applications, though they are above chance level and outperform several baselines.
What’s more, they added, the prediction accuracy and reliability scores obtained from 42 participants were “very promising”. The number of participants was small but in the future, more data could serve to support greater accuracy.
One concern mentioned is that AI as a mechanism for assigning personality types can be abused when in the wrong hands with ethical issues thrown in question.
“Robots and computers are currently socially ignorant and don’t adapt to the person’s non-verbal signals,” noted researcher Bulling . “When we talk, we see and react if the other person looks confused, angry, disinterested, distracted, and so on. Interactions with robots and computers will become more natural and efficacious if they were to adapt their interactions based on a person’s non-verbal signals.”