It used to be that psychologists would have to administer a litany of tests to uncover the structure of someone’s personality. Not anymore. Nowadays, semi-accurate personality inferences can be made simply by analyzing a person’s online behavior. Enter Suzie’s clicks, likes, posts, and web visits into a whizzy machine learning algorithm and out comes her personality profile. No questioning necessary.

New research published in the Proceedings of the National Academy of Sciences takes this idea one step further. A team of scientists led by Clemens Stachl of Stanford University found that three of the Big Five personality dimensions — namely, extraversion, conscientiousness, and openness to experiences — could be accurately predicted from people’s smartphone usage patterns. The other two dimensions — agreeableness and emotional stability — remain hidden from view, at least for now.

“We assessed personality in terms of the Big Five dimensions, the most widely used and well-established system in psychological science for organizing personality traits,” state the researchers. “This taxonomy describes human personality in terms of five broad and relatively stable dimensions: openness, conscientiousness, extraversion, agreeableness, and emotional stability, with each dimension subsuming a larger number of more specific facets.”

Using the Big Five taxonomy as a starting point, the researchers tested whether people’s smartphone usage patterns — such as their app usage, music consumption, communication and social behavior, mobility behaviors, overall phone activity, and daytime versus nighttime phone activity — would prove useful in predicting their personality traits. They found that it was. Specifically, the researchers successfully predicted 57% of personality traits from behavioral patterns derived from people’s smartphone data.

Not surprisingly, some personality traits were easier to predict than others. The researchers found ‘sociableness’ to be the most predictable personality trait and ‘good naturedness’ to be the least predictable trait. Other traits that were highly predictable from the smartphone data were ‘love of order,’ ‘sense of duty,’ ‘assertiveness,’ and ‘self consciousness.’

Which behaviors were most effective at predicting the various dimensions of personality? Among the three predictable dimensions of the Big Five personality taxonomy (extraversion, conscientiousness, and openness), the number of nightly calls was the best predictor of extraversion, the use of the weather app at night was the best predictor of conscientiousness, and the length of one’s text messages was the best predictor of openness.

The researchers also draw attention to the privacy concerns related to this research. They conclude, “We should not underestimate the potential negative consequences of the routine collection, modeling, and uncontrolled trade of personal smartphone data. For example, organizations and companies can obtain information about individuals’ private traits (e.g., the Big Five personality traits), without the personality information ever being deliberately provided or explicitly requested. Mounting evidence suggests that these data can and are being used for psychological targeting to influence people’s actions, including purchasing decisions and potentially voting behaviors, which are related to personality traits.”

Forbes