Researchers at the University of Cambridge and Stanford University pitted friends and family against an algorithm to find out which was better at determining a subject’s personality. The friends filled out a survey while the program computed the subject’s Facebook “likes.”
The researchers rated subjects on openness, conscientiousness, extraversion, agreeableness, and neuroticism.
They found that, in most cases, the algorithm was better able to predict a person’s personality traits than close friends were able to do.
“Using several criteria, we show that computers’ judgments of people’s personalities based on their digital footprints are more accurate and valid than judgments made by their close others or acquaintances (friends, family, spouse, colleagues, etc.),” the researchers wrote.
The research was aimed at creating programs that could better assess personality traits in the hopes of replacing human judgments in situations where such information is needed.