How social media data could predict basic personality traits and attributes

A recent study published in the Journal of Personality shows how social media information could predict basic personality traits and attributes by using machine learning. The study was conducted by the National Institute of Information and Communications Technology.

In past research, data from social networking sites have shown certain basic personality traits associated with the Big 5. In the new study, researchers delved into the types of social media-based information needed to analyze and predict personality traits and attributes.

239 participants, the majority of whom were men, were recruited for the study. The participants took part in personality tests measuring 24 traits and attributes.

“The study collected social media information from 239 participants (156 men, 83 women; average age 22.4 years old) who also took personality tests that measured 24 personality traits and attributes (52 subscales). Of the 52 subscales, the Twitter information could be reliably used to predict 23 of them,” a news release states.

In their study, researchers uncovered that analyzing the following four different types of users’ behaviors on social networking sites gave them more insight into a range of personality traits and attributes.

According to researchers: network features, time, word statistics, and word usage, all contribute to their determination of a user’s personality traits with high accuracy.

Their analysis of those four factors showed that numerous personality traits, such as autism, empathy, extraversion, could be predicted.

“These results reveal that the different types of social networking services (SNS) information can collectivity predict wider human traits and attributes than previously recognized, and also that each information type has unique predictive strengths for specific traits and attributes, suggesting that personality prediction from SNS is a powerful tool for both personality psychology and information technology,” the co-authors concluded in their findings.

More Stories
Low-frequency rTMS may provide some improvement to episodic memory