As surveillance methods get ever more complex and invasive, for example facial recognition and new gait recognition techniques (software which uses the patterns in how you walk to identify you) the tools available may soon be joined by artificial intelligence that uses eye tracking to predict the type of personality you are.

The University of South Australia in partnership with the University of Stuttgart, Flinders University and the Max Planck Institute for Informatics in Germany, have shown that state-of-the-art machine-learning algorithms demonstrate a link between personality and eye movements.

AI Peers Into the Window of the Soul

According to the original study, eye movements are a window into the mind and a rich source of information on who we are, how we feel, and what we do. The research looked into the AI eye tracking movements during everyday tasks in order to predict aspects of subjects personality. 42 participants were subjected to eye tracking while they ran an errand on a university campus and subsequently assessed their personality traits using well-established questionnaires.

Using a state-of-the-art machine learning method and a rich set of features encoding different eye movement characteristics, they were able to reliably predict four of the Big Five personality traits (neuroticism, extraversion, agreeableness, conscientiousness) purely by eye tracking each individual.

University of South Australia’s Dr Tobias Loetscher said the study provided new links between previously under-investigated eye movements and personality traits and delivered important insights for emerging fields of social signal processing and social robotics.

“There’s certainly the potential for these findings to improve human-machine interactions,” Dr Loetscher said.

“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.

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

Couched in Controversy

This isn’t new territory despite sounding futuristic and like a scene from Minority Report. Previous studies have reported relationships between personality traits and eye movements suggesting that people with similar traits tend to move their eyes in similar ways.

However this is dangerously close to other studies where facial traits have been linked to predicting sexual orientation, physical build and mental states and proven to be anything but fool-proof and conclusive. Physiognomy dates as far back to the Greeks and has been used in early criminology where in the 19th century you could be labelled a criminal just because you had ‘that look about you’.

With facial recognition already called into question, and the Australian government wanting to sell biometric data to the highest bidder, the need for stricter regulation and ethical control over methods like AI eye tracking grows ever stronger.