Artificial intelligence can predict human personality traits by tracking eye movements, according to a new study.

Researchers at the University of South Australia created a machine-learning algorithm that can analyze a person’s eye movements and recognize four of the five big personality traits: neuroticism, extraversion, agreeableness and conscientiousness.

The software opens up the possibility of one day developing robots that are in tune with human signals and socialization.

The research is published in the journal Frontiers in Human Neuroscience.

The University of Stuttgart, Flinders University and the Max Planck Institute for Informatics in Germany collaborated in the research.

The study

The researchers recruited 42 participants and tracked their eye movements while they performed everyday tasks around a university campus.

By doing this, the researchers were able to analyze the effectiveness of the study in the natural world, rather than in a lab.

“A lot of the research we do in psychology is conducted in highly controlled laboratory settings. For example, people have to respond to things we present on a computer screen and, based on their responses, we develop theories of human behaviour,” said Dr. Tobias Loetscher, a senior lecturer in the School of Psychology, Social Work and Social Policy at the University of South Australia.

“An important question is to what degree these theories are valid if they were collected in rather artificial and unnatural laboratory settings. Thus, one important motivation for this research was to conduct the experiment in natural settings – the real world – and to see whether we can replicate previous findings which showed a link between eye movements and personality traits.”

Each of the participants was fitted with a 60 Hz head-mounted video-based eye tracker that recorded gaze data and high resolution video

Then, the researchers assessed personality traits by giving the participants three established self-reporting questionnaires.

The findings

After comparing the gaze data collected by the machines with the personality questionnaires, the researchers concluded that people’s eye movements can reveal whether they are social, conscientious, or curious.

While previous studies have shown a link between personality traits and eye movement, this is the first of its kind to analyze the relationship via artificial intelligence.

This research not only validates previous studies, but also demonstrates that certain eye movement characteristics can predict personality traits.

Conclusion

Loetscher explained that the research can be used to make human-machine interactions more natural in the future.

“Human-machine interactions are currently unnatural. The ATM, computer, phone don’t adapt to our mood or the current situational context,” he said.

“It doesn’t matter whether I’m happy, angry, confused, ironic, irritated – the computer is not empathic and not adapting to my situation. If we manage to provide computers with the ability to sense and understand human social signals, the interactions will become more natural and pleasant.”

Additionally, the researchers have discussed using the technology for clinical populations, such as in patients with dementia.

“I’d like to study whether eye movements can help to predict future cognitive impairments,” said Loetscher.

The research puts a new twist on the age-old notion that the “eyes are the window to the soul” — perhaps instead, the eyes are the window to personality and health.