Myers-Briggs Personality Classification and Personality-Specific Language Generation Using Pre-trained Language Models

TL;DR

This paper explores using pre-trained language models to classify MBTI personality types from text and investigates fine-tuning BERT for personality-specific language generation, with promising accuracy results.

Contribution

It introduces a method for MBTI classification using language models and demonstrates the potential for personality-specific language generation.

Findings

Accuracy of 0.47 for full MBTI type prediction

Accuracy of 0.86 for predicting at least 2 types

Potential applications in psychology and empathetic AI systems

Abstract

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.