5.3
JPT Research Digest
The interdependency of the diction and MBTI personality type of online users.
Choi, S. (2021). The interdependency of the diction and MBTI personality type of online users. American Journal of Applied Psychology, 10(1), 21. doi.org/10.11648/j.ajap.20211001.14 |
This paper offers insight into how MBTI® personality types may influence the words employed by online users on social media platforms such as Twitter and YouTube. The study utilized computer programming, data analysis, and machine-learning algorithms to analyze individuals' online posts to help identify users' MBTI personality type.
The project analyzed 433,750 individual online posts and identified algorithms most effective in predicting MBTI type preferences. Individuals were asked to volunteer their accounts for analysis. Of those who offered to take part in the study, the four most frequent types had preferences for Introversion (I) and Intuition (N). The four least frequent types preferred Extraversion (E) and Sensing (S). Most data (80%, selected randomly) were used to train the algorithms and the remainder to test the machine-learning for accuracy and specificity. Word clouds were formed displaying the words most used by each type. (Three word clouds are included in the paper for INTP, ENFJ, and words most used across all types.)
The algorithms were able to predict individual type preferences with an average accuracy of 80%, and four-letter MBTI type with approximately 52% accuracy. Future research might focus on written diaries or journals that may provide different results as those tend to use a broader vocabulary, according to the author, producing different machine-learning algorithms which may enhance results for future research.
ARTICLE PERMALINK: https://www.myersbriggs.org/research-and-library/journal-psychological-type/interdependency-diction-mbti-online-users/
ARTICLE COMMENTS: