According to this new study, published in PNAS, a correlation can be established between our mobile use (which applications we use, how we use music, day / night use, etc.) and our personality (according to the Big Five).
The research team led by the Stanford psychologist Markus Bühner set out to determine whether conventional data collected passively by smartphones (such as times or frequencies of use) provides information on the personality of users.
In psychology, the Big Five Model (or simply Big Five) is a taxonomy or classification of personality traits that analyzes the composition of five personality dimensions in its broadest sense.
The five main traits or factors are traditionally referred to as:
Openness to experience (inventive / curious vs. consistent / cautious) OR
Awareness (efficient / organized vs. quirky / sloppy) C
Extraversion (sociable / energetic vs. lonely / reserved) E
Amiability (friendly / compassionate vs. defiant / insensitive) A
Neuroticism (susceptible / nervous vs. resistant / safe) N
Smartphones enjoy high adoption rates around the world. Rarely more than an arm’s length away, these sensor-rich devices can be easily reused to collect rich and extensive records of their users’ behaviors (eg, location, communication, media consumption).
The team of researchers recruited 624 volunteers for their project PhoneStudy. Participants agreed to complete a lengthy questionnaire describing their personality traits and to install an app that had been specially developed for the study on their phones for 30 days. The application was designed to collect coded information related to user behavior.
The researchers were primarily interested in data related to communication patterns, social behavior and mobility, along with the users’ choice and consumption of music, the selection of applications used and the temporal distribution of their phone use throughout the day.
Then, all data on personality and smartphone use was analyzed with the help of machine learning algorithms, which were trained to recognize and extract patterns from behavioral data and relate these patterns to information obtained from surveys of personality.
The use of the smartphone would thus correlate such dimensions of personality:
Music volume predicts openness to ideas Using the weather app predicts responsibility. Wake-up time predicts ambition Nighttime phone ringing predicts extraversion Use of sports apps predicts openness to aesthetics
According to the study authors, the accuracy of these predictions is similar to that found for fingerprint-based predictions of social media platforms and demonstrates the possibility of obtaining information about people’s private traits from passively collected behavior patterns from their smartphones.
Usually, the results point to both benefits (eg, in research settings) as well as the dangers (eg, privacy implications, counseling) presented by the widespread collection and modeling of behavioral data obtained from smartphones.