Artificial Intelligence: This Algorithm Can Predict Your Personality by Tracking Your Eye Movements

Our eyes allow us to perceive the world around us, but they are also a window into the mind. In fact, an emerging body of research suggests that the way in which we move our eyes is affected by our personality.

Studies looking into this topic have found 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.

Recently, an international team of researchers from institutions in Australia and Germany tried to understand more about the link between personality and eye movements by developing a machine learning algorithm—a type of computer code that learns without the need to be specifically programed—New Scientist reports.

For a new study, published in the journal Frontiers in Human Neuroscience, the researchers gave 42 students at Flinders University in south Australia special eye-tracking glasses. They then asked the participants to walk around campus and visit a shop, as well as complete a questionnaire, which scored them on the "big five" personality traits: openness to experience, conscientiousness, extraversion, agreeableness and neuroticism.

Using the algorithm, the scientists found they were able to predict four of those traits—neuroticism, extraversion, agreeableness, conscientiousness—as well as perceptual curiosity, based only on the eye-movement tracking data.

At present, their technique is only 7 to 15 percent better than chance at predicting these personality traits, but the scientists note that they only had data from 42 people. As the algorithm receives more eye-tracking data, its predictions will become increasingly accurate, they say.

A new machine learning algorithm can predict your personality just by tracking your eye movements. KAREN BLEIER/AFP/Getty Images

Furthermore, the findings "revealed new relations between previously neglected eye movement characteristics and personality," the authors wrote in the study. For example, pupil diameter was found to be important for predicting neuroticism but less useful for predicting other traits.

The findings of the study could enable the design of computer systems—including robots, smartphones and self-driving cars—which could automatically read users' personalities based on eye-tracking data and are able customize their experience accordingly.

Although, as consumers become ever more concerned about the quantities of data they are handing over to tech companies, this kind of technology may not appeal to everyone.