AI Can Guess Your Personality Type by Tracking Your Eyes

By: | August 18th, 2018

It’s often said that the eyes are the window to the soul. And there is definitely some truth to it — our eye movements signal things about the way we think and feel. Now, scientists have revealed an AI that can predict your personality type simply by watching your eyes.

Developed by the University of South Australia, in collaboration with the University of Stuttgart, Flinders University, and the Max Planck Institute for Informatics in Germany, this AI identifies four of the Big Five personality traits (openness to experience, conscientiousness, extraversion, agreeableness, and neuroticism) in a human subject by merely tracking eye movement.

Tobias Loetscher, one of the lead researchers on the project, said, “Thanks to our machine-learning approach, we not only validate the role of personality in explaining eye movement in everyday life, but also reveal new eye movement characteristics as predictors of personality traits.”

For testing the accuracy of their algorithms, researchers tracked the eye movements of 42 participants as they undertook everyday tasks around a university campus. Participants were also asked to fill out the standard personality questionnaire.

Once algorithms analyzed eye movements and made predictions about each participant’s personality type, these predictions were compared with personality traits as revealed by the questionnaires.

Researchers found that the AI was able to make reliable guesses. Loetscher said, “People are always looking for improved, personalized services,” he explained. “However, today’s robots and computers are not socially aware, so they cannot adapt to non-verbal cues.”

“This research provides opportunities to develop robots and computers so that they can become more natural, and better at interpreting human social signals.”

Nidhi Goyal

Nidhi is a gold medalist Post Graduate in Atmospheric and Oceanic Sciences. You can also find Nidhi on Google+.

Google+ 

More articles from Industry Tap...