Personality and emotion—A comprehensive analysis using contextual text embeddings

Personality and emotional expression have always been deeply related. In this study, the authors link MBTI^® personality preferences to Ekman’s six emotions (joy, sadness, fear, anger, disgust, surprise). Their objective was to automate the process of determining the relationships between personality traits and emotions.

The study has two phases: one in which machine learning models are trained on datasets labeled with emotions and the second in which the models then trained the patterns of emotional expression they learned on targeted datasets of social media posts in which the MBTI type of the users was known.

With an overall accuracy rate of 85.23%, the study finds links between each MBTI preference and the Ekman emotions. The study reveals that preferences for Extraversion (E), Sensing (S), and Feeling (F) are more likely to share joyful and surprising emotional posts, while preferences for Intuition (N), Thinking (T), and Perceiving (P) traits tend to express negative emotions such as anger and disgust. Conversely, Introversion (I), Intuition (N), Thinking (T), and Judging (J) personalities are more inclined to share posts reflecting fear and sadness.

This study provides insights on how individuals with different personality preferences express emotions on social media. Tending to be more present and open to situations and others, preferences for Extraversion, Sensing, and Feeling might be expected to express more positive emotions, just as preferences for Intuition and Thinking may tend to more negative feelings as these preferences can draw a person away from the present or have a critical perspective on the present.

ARTICLE PERMALINK: https://www.myersbriggs.org/research-and-library/journal-psychological-type/emotional-expression-through-type-preferences/

ARTICLE COMMENTS: