A new study investigates the use of Artificial Intelligence (AI) to identify personality types based on tracking eye movements.
It’s a common enough idea that the eyes are the window to the soul, and that when playing poker, some experienced players wear sunglasses so that their eyes don’t give the game away to their opponents; and now scientists from the University of Australia have used Machine Learning to suggest a connection between individuals personalities and the movement of their eyes.
The study, published this month in the Frontiers in Human Neuroscience, states that how peoples eyes move when looking at certain images, means that Artificial Intelligence can take a pretty good guess on the type of personality you possess, just by looking at your eyes.
42: The answer to everything?
In order to carry out the experiment, the researchers gave 42 students special eye-tracking glasses and asked them to complete a certain number of tasks on campus, including an everyday mundane one of visiting a specific shop.
Afterwards, students were asked to complete a questionnaire, which then scored them on common “big five” personality traits: openness to experience, conscientiousness, extraversion, agreeableness and neuroticism.
Although the study was conducted by University of South Australia, it was a global effort, and was done in partnership with the University of Stuttgart, Flinders University and the Max Planck Institute for Informatics in Germany.
The glasses used in the study tracked its users eye movements, recording them, for cutting edge AI machine-learning algorithms to find a link between personality and eye movements.
“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,” said neuropsychologist Tobias Loetscher from the University of South Australia.
While previous studies have of course already ascertained that people with similar traits tend to have similar movements of the eyes, this is the first to have used Artificial Intelligence to correctly identify personality types based on eye movement.
“This research provides opportunities to develop robots and computers so that they can become more natural, and better at interpreting human social signals,” said Loetscher.
Using a custom designed algorithm, scientists found that the machine learning software was able to predict four of the major personality traits, as well as perceptual curiosity, based only on data provided by eye tracking.
A word of warning.
The robots wont however be taking over any time soon. At present, the AI software was only somewhere between 7 to 15 percent better than chance at predicting these personality traits. While that may seem like a small amount, in statistical terms that 7-15% is a significant number.
The scientists also noted that in this initial study, that they only had data from 42 people. As the algorithm receives more eye-tracking data, its predictions should become increasingly accurate over time.