Scientists use phone movement to predict personality types

It turns out the pattern of how your mobile phone moves around says a lot about your personality.

Researchers used data from mobile phone accelerometers - the tiny sensors tracking phone movement for step-counting and other apps – to predict people’s personalities.

RMIT University computer scientist Associate Professor Flora Salim said previous studies had predicted personality types using phone call and messaging activity logs, but this study showed adding accelerometer data improved accuracy

“Activity like how quickly or how far we walk, or when we pick up our phones up during the night, often follows patterns and these patterns say a lot about our personality type,” said Salim, a leading expert in human mobility data.

Physical activity is proven to have a strong correlation with human personality. Therefore, researchers analysed physical activity features from different dimensions like dispersion, diversity, and regularity.

Key findings from the study:

People with consistent movements on weekday evenings were generally more introverted, while extroverts displayed more random patterns, perhaps meeting up with different people and taking up unplanned options.
Agreeable people had more random activity patterns and were busier on weekends and weekday evenings than others.
Friendly and compassionate females made more outgoing calls than anyone else.
Conscientious, organized people didn’t tend to contact the same person often in a short space of time.
Sensitive or neurotic females often checked their phones or moved with their phones regularly well into the night, past midnight. Sensitive or neurotic males did the opposite.
More inventive and curious people tended to make and receive fewer phone calls compared to others.

RMIT University computer scientists Dr Flora Salim, Nan Gao and Dr Wei Shao.

Study lead author and RMIT University PhD student, Nan Gao, said the potential applications from this research were exciting.

“There are applications for this technology in social media with friend recommendations, online dating matches and targeted advertising, but I think the most exciting part is what we can learn about ourselves,” said Gao.

“Many of our habits and behaviours are unconscious but, when analysed, they tell us a lot about who we really are so we can understand ourselves better, resist social pressure to conform and to empathize with others."

"Most importantly, being who we truly are can make our experience of life richer, more exciting and more meaningful.”

“In Ancient Greece there is a saying about knowing yourself as the beginning of wisdom, applications like this can really help to reveal who we are to ourselves.”

The results were analysed in accordance with the Big Five personality traits, which are:

Extraversion: how energetic, sociable and talkative you are.
Openness: how curious and inventive you are.
Agreeableness: how friendly and compassionate, rather than suspicious and hostile, you are to others.
Conscientiousness: how organized, efficient and careful you are.
Neuroticism: how nervous and sensitive, rather than confident and secure, you are.

The team’s study ‘Predicting Personality Traits from Physical Activity Intensity’ has just been published in the IEEE Computer journal.

This work was funded through an Australian Research Council Linkage project between Swinburne University of Technology, RMIT University and Aurecon.

The study was conducted on a public dataset gathered from participants at a US university. As findings may vary in a different group, the team will next collect data from Australian participants to further test the effectiveness of their research.

Story: Michael Quin

Technology

24 July 2019

Technology

24 July 2019

Research
Science and technology
Industry

Engage

Related News

RMIT researchers win prestigious 2018 Victoria Fellowship

RMIT researchers Sumeet Walia and Flora Salim have been awarded Victoria Fellowships for their outstanding work in nanotechnology and data science respectively.

Global study on the impact of social media for citizen engagement

RMIT and Oslo Metropolitan University researchers are studying the use of social media to support citizen participation in local government in a study funded by The Research Council of Norway.

New blockchain courses to address skills gap

With blockchain expertise in high demand, but considerable gaps preventing this demand from being met, RMIT has announced two new courses to provide students with these necessary future skills.

Girls bring the WOW factor

Pop megastar Beyoncé sang about girls running the world and that’s what more than 500 school students were empowered to do at the Girled World WOW Summit at RMIT.

Subscribe to RMIT NewsSubscribe

Acknowledgement of Country

RMIT University acknowledges the people of the Woi wurrung and Boon wurrung language groups of the eastern Kulin Nation on whose unceded lands we conduct the business of the University. RMIT University respectfully acknowledges their Ancestors and Elders, past and present. RMIT also acknowledges the Traditional Custodians and their Ancestors of the lands and waters across Australia where we conduct our business. - Artwork created by Louisa Bloomer

More information

Scientists use phone movement to predict personality types