AI links eye movements to personality, for better human-bot interactions
- 03 August, 2018 07:26
Improved human-bot interactions for better personalisation may not be as far off as we think, thanks to new research linking personality to eye movements using artificial intelligence (AI).
The research uses state-of-the-art machine-learning algorithms to demonstrate a link between personality and eye movements, and was developed by the University of South Australia in partnership with the University of Stuttgart, Flinders University and the Max Planck Institute for Informatics in Germany.
UniSA’s Dr Tobias Loetscher said the research, using special glasses, delivers 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,” he 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.
Findings show people’s eye movements reveal whether they are sociable, conscientious or curious, with the algorithm software reliably recognising four of the Big Five personality traits: Neuroticism, extroversion, agreeableness, and conscientiousness. There was no link demonstrated with openness, but given the small size of the trial, this doesn’t mean there isn’t one.
“And 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,” Loetscher said.
“The predictive power is relatively modest at this stage. Eye movements wouldn’t be enough on its own, it would need to be combined with voice or facial recognition for the robot to understand what the humans are feeling. It would need to be a combination of a few things, rather than just eye movement. But the technology is improving all the time.
“There is also the problem of invasion of privacy around this kind of technology, that’s a big issue for marketers to consider as they move forward.”
Researchers tracked the eye movements of 42 participants as they undertook everyday tasks around a university campus, and subsequently assessed their personality traits using well-established questionnaires.
The research wasn’t originally undertaken to assess personality and eye movements, it was designed with a more clinical intent in mind.
“We tested eye movements as a biomarker for future cognitive impairment or cognitive decline. There is some research to show that abnormality in eye movement may come before memory decline,” Loetscher said.