The Myers-Briggs Type Indicator (MBTI) is a popular personality metric that uses four dichotomies as indicators of personality traits. This paper examines the use of pre-trained language models to predict MBTI personality types based on scraped labeled texts. The proposed model reaches an accuracy of 0.47 for correctly predicting all 4 types and 0.86 for correctly predicting at least 2 types. Furthermore, we investigate the possible uses of a fine-tuned BERT model for personality-specific language generation. This is a task essential for both modern psychology and for intelligent empathetic systems.
Cite
@article{arxiv.1907.06333,
title = {Myers-Briggs Personality Classification and Personality-Specific Language Generation Using Pre-trained Language Models},
author = {Sedrick Scott Keh and I-Tsun Cheng},
journal= {arXiv preprint arXiv:1907.06333},
year = {2019}
}