A new personality study published in Proceedings of the National Academy of Science coolly walks a fine line between being the cleverest and the most terrifying thing imaginable.
It examines the extent to which personality dimensions can be predicted from six classes of behaviour in a person’s smartphone use: communication and social behaviour; music consumption; app usage; mobility; overall phone activity; and day- and night-time activity.
As the authors note: “Smartphones enjoy high adoption rates around the globe. Rarely more than an arm’s length away, these sensor-rich devices can easily be repurposed to collect rich and extensive records of their users’ behaviours.”
Also noted: smartphones pose “serious threats to individuals’ privacy”.
Led by Clemens Stachl, of Stanford University, US, the researchers collected behavioural data from the phones of 624 volunteers over 30 days; it included more than 25 million smartphone datalogging events.
The team’s results revealed that an individual’s “Big Five” personality traits – openness, conscientiousness, extraversion, agreeableness and emotional stability (or neuroticism, if you prefer) – were partially predictable from their smartphone usage patterns.
The findings, they say, highlight both the potential of widespread collection of smartphone activity data and the privacy implications of such collection.
They noted that the accuracy of their predictions in relation to the six behaviour classes is similar to those based on digital footprints from social media platforms.
“It has been well documented that ‘digital footprints’ derived from social network platforms (e.g. Facebook likes) can reveal individuals’ psychological characteristics, such as their personality traits,” they write.
“This is consequential because the Big Five personality traits have been shown to predict a broad range of life outcomes in the domains of health, political participation, personal and romantic relationships, purchasing behaviours, and academic and job performance.”
While lauding the fact that “data-driven inferences about individuals’ personality traits” hold great potential for research, the authors observe that this also has “major implications for individual privacy because they allow for personality-based targeting and manipulation”.
And, in regards to privacy, they called out the even-darker side of smartphones: “[They] can collect a far broader, ﬁne-grained array of daily behaviours than can be scraped from social media platforms.”
There’s no end to vexation regarding the collision of data collected and examined for the greater good and privacy implications, but the authors attempt a reasoned response.
“A large portion of current economic and scientiﬁc progress depends on the availability of data about individuals’ behaviours,” they write in conclusion.
“The smartphone represents an ideal instrument to gather such information. Therefore, our results should not be taken as a blanket argument against the collection and use of behavioural data from phones. Instead, the present work points to the need for increased research at the intersection of machine learning, human computer interaction, and psychology that should inform policy makers.
“We believe that to understand complex social systems, while at the same time protecting the privacy of smartphone users, more sophisticated technical and methodological approaches combined with more dynamic and more transparent approaches to informed consent will be necessary…
“These approaches could help balance the tradeoff between the collection of behavioural smartphone data and the protection of individual privacy rights, resulting in higher standards for consumers and industry alike.”
Read science facts, not fiction...
There’s never been a more important time to explain the facts, cherish evidence-based knowledge and to showcase the latest scientific, technological and engineering breakthroughs. Cosmos is published by The Royal Institution of Australia, a charity dedicated to connecting people with the world of science. Financial contributions, however big or small, help us provide access to trusted science information at a time when the world needs it most. Please support us by making a donation or purchasing a subscription today.