Artificial Intelligence Algorithm can Predict Your Personality by Looking into Your Eyes | Robotics

Even though our eyes aren’t necessarily windows to the soul, they may at least serve as the keyhole to our personalities – based on eye movement alone, a new artificial intelligence algorithm can glean a wealth of data on our personal characteristics.

Using state-of-the-art machine-learning techniques, researchers from the University of South Australia, the University of Stuttgart, Flinders University and the Max Planck Institute for Informatics in Germany demonstrate a link between different activities and their accompanying patterns of eye movement.

New study corroborates previous findings that eye movements are robust predictors of human personality traits. Image credit: Tookapic via pexels.com, CC0 Public Domain.

The research team tracked the eye movements of 42 volunteers who were asked to engage in everyday activities around the university campus, and then assessed their personalities using well-established questionnaires.

Results showed that eye movements can reliably indicate one’s personality type and reveal how people score on the Big Five inventories, which track such individual traits as neuroticism, extraversion, agreeableness, and conscientiousness.

“There’s certainly the potential for these findings to improve human-machine interactions,” said Dr Tobias Loetscher of the University of South Australia. “People are always looking for improved, personalised services. However, today’s robots and computers are not socially aware, so they cannot adapt to non-verbal cues.”

According to Loetscher, new research into the relationship between eye movements and personality ushers in the possibility of building systems with the goal of making our interactions with machines less jarring, thereby increasing human well-being.

The predictions were not perfect, but well above chance-level, and matched up with previous research done on personality traits and eye movements.

One of the key advantages of the new study is that it used people engaged in their everyday lives in a normal setting, rather than under highly artificial lab conditions.

“And 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.”

The study was published on 13 April 2018 in the journal Frontiers in Human Neuroscience.

Source: unisa.edu.au.