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 inter‐personal 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 extraversion well, while timing was linked with things like intelligence and pro- versus anti-social behavior.
As for mental health predictors, “Emotional words had strong predictive power, with the use of more negative words and less positive words predicting delusion, depression, and anxiety,” they write.