How Social Media Activity May Predict Personality & Mental Health Traits

For the study, researchers Kazuma Mori and Masahiko Haruno had machine learning models predict and find connections between personality traits and social media use, based on things like word choice, time, and existing statistics.

They specifically looked for Big Five personality scores (extroversion, neuroticism, agreeableness, conscientiousness, and openness), intelligence scores, life satisfaction (like happiness and self‐esteem), and consumption levels of alcohol and cigarettes.

Based on the findings, the researchers say there are four categories of social media info, which can predict 23 different "subscales" of personality. Namely, language and "network features" (things like number of tweets, number of followers, number of replies, mentions, etc.) appeared to be the strongest predictors.

"We validated our hypothesis that the network and word statistics information, respectively, exhibit unique strengths for the prediction of interpersonal traits such as autism, and mental health traits such as schizophrenia and anxiety," the study authors note in their research. "We also found that intelligence is predicted by all four types of social network service information."

For instance, "our analysis showed that people with high verbal intelligence tended to tweet frequently and were more favorited," the authors write. "These people also showed stable timing in their replies."

Network information also predicted things like extroversion well, while timing was linked with things like intelligence and pro- versus anti-social behavior.

Overall, the areas that saw the most predictability based on social media were mental health, empathizer‐systemizer (whether you're more emotions- or rule-based), Big Five personality, intelligence, life satisfaction, and drinking or smoking.

And until now, experts really didn't know just how much of personality could be extracted and understood from tweets and social media posts alone. "Each information type has unique predictive strengths for specific traits and attributes," Mori and Haruno say, "suggesting that personality prediction from social networking services is a powerful tool for both personality psychology and information technology."