Eye tracking AI
Apple's new patent reveals it is working on new technologies capable of predicting where a person will look next. REUTERS/Aly Song

Eyes are often referred to as a window to the soul, one that could reveal what a person is feeling deep inside.

Be it fear, guilt, sorrow or happiness, human peepers can hide a range of emotions. Not everyone can read them easily, but a handful of studies have shown that some specific movements of the eye can indicate what a person was feeling and thinking.

Now, using these movements, an international team of researchers has developed an artificial intelligence (AI) that can track the eye-movements and predict what kind of personality a person has.

The system, which basically is a state-of-art machine learning algorithm, tracks the motion of the eye and then matches those movements to five personality traits — openness, conscientiousness, neuroticism, agreeableness, and extraversion.

“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,” neuropsychologist Tobias Loetscher from the University of South Australia said in a statement.

Loetscher and colleagues tested the functionality of the system by calling 42 volunteers for the study. Each of the participants first answered a series of questions designed to assess what kind of personality trait they had.

Once the questionnaire was filled, the participants were asked to wear an eye tracker and carry on with their day to day tasks around the campus. This way their eye movements were tracked and recorded during open-environment interactions.

“This research has tracked and measured the visual behavior of people going about their everyday tasks, providing more natural responses than if they were in a lab,” Loetscher added.

After this, the data collected by the eye-tracker was fed into the machine learning software. Much to everyone’s surprise, the system managed to isolated eye movement of each student with their respective personality type, revealing whether they are curious, sociable, or conscientious.

The results from the AI, as scientists described, were not exactly similar to the character traits defined from the questionnaire, but they believe further improvement in this area could dramatically change how machines interact with their human counterparts.

“People are always looking for improved, personalized services. However, today’s robots and computers are not socially aware, so they cannot adapt to non-verbal cues,” Loetscher explained. “This research provides opportunities to develop robots and computers so that they can become more natural, and better at interpreting human social signals.”

That said, it is also worth noting that a machine's ability to track our eyes and determine what we’re feeling could also raise some privacy-related concerns. People could leverage these capabilities to peer into the eyes of an unaware individual and predict their emotions and feelings, without their consent.