AI links eye movements to personality, for better human-bot interactions

New study has potential to make robots socially aware by better gauging consumer's emotional and psychological responses

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.

Follow CMO on Twitter: @CMOAustralia, take part in the CMO conversation on LinkedIn: CMO ANZ, join us on Facebook: https://www.facebook.com/CMOAustralia, or check us out on Google+:google.com/+CmoAu   

 

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.
Show Comments

Blog Posts

Designing for a cashless society

More movement has been made toward a cashless society recently, and already we are starting to see enormous implications across our society.

Katja Forbes

Founder and chief, sfyte

Setting advertising objectives for financial performance

I’ll often be talking to clients and at some point say, ‘the most important thing is justifying price’. Then moments later, ‘the most important thing is increasing the size of your customer base’.

Kyle Ross

Strategist, TRP

5 common mistakes to avoid in scalable customer experience

CX is about future-proofing your business by ensuring that your commercial model is always looped into your customers' needs, perceptions, values, beliefs, motivators, and detractors.

Tom Uhlhorn

Founder and strategy director, Tiny CX

This is pure vomit material. Self congratulatory blurbs. No evidence of any innovation or actual value created. Most marketers have compl...

Bobbo

Announcing the CMO50 for 2018

Read more

Unfortunately, the title "AdTech Magic Quadrant" is misleading as it only represent a fraction of the ecosystem. It it is a useful docume...

Ludovic Leforestier

Report: Gartner recognises the best adtech players in Magic Quadrant

Read more

Thanks for writing about chatbots. Definitely bots have the exciting future when it comes to customer engagement, transactional and conve...

Giridhar Prathap Reddy

Australian Open chalks up strong ticket sales with chatbot

Read more

Hello, where are the explanations of all the levels explained? I'd like to review this with a couple of colleagues. Thanks.

Melinda Gonzalez

CMO launches CMO CX, debuts customer experience maturity assessment

Read more

A great and accurate commentary - today we rarely get true personalisation. On web journeys cookies or logins remember who we are, what w...

Ian Moyse

Salesforce: Personalisation is a long way off what consumers now expect

Read more

Latest Podcast

More podcasts

Sign in