Personality recognition from text based on MBTI model

• Main Author: Yi, Joceline Jia Xin
• Other Authors: Erik Cambria
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/166165
• Institution: Nanyang Technological University

The Myers-Briggs Type Indicator (MBTI) is a widely used personality assessment tool that categorizes individuals into one of 16 different personality types based on their preferences for different psychological dichotomies. In recent years, there has been a growing interest in using natural language processing (NLP) techniques to predict an individual's MBTI personality type based on their written text. This study presents an investigation into the effectiveness of various NLP methods for predicting MBTI personality types from textual data. A dataset of blog posts from individuals who have self-reported their MBTI type was collected and pre-processed for use in the study. Four different NLP methods were implemented and evaluated, including feature engineering, machine learning, neural networks, and transfer learning techniques. Ensemble learning techniques were also explored in this study for the task of multi-class classification.