Scholarlink

In modern psychology, personality exploration is pivotal, with the Myers-Briggs Type Indicator (MBTI) being a widely recognized tool. It categorizes individuals into 16 distinct personality types, providing insights into human behavior. The field has evolved with the rise of personality computing, where digital, data-driven approaches enhance personality assessments’ accuracy. By leveraging text classification algorithms, researchers can analyze extensive digital data, surpassing the limitations of traditional assessments. This fusion of machine learning and personality research marks a significant advancement, offering deeper insights into human behavior. We tested many models: Naïve Bayes, logistic regression (LR), random forest (RF), K-nearest neighbors (KNN), stochastic gradient descent (SGD), and support vector classifier (SVC). LR and SGD were proved to have relatively high precision on introversion/extroversion and intuition/sensing dimensions. RF excelled in the judging/perceiving dimension, achieving perfect accuracy, highlighting the variability in model performance across personality traits. These findings underscore the potential for refined personality insights.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Personality Prediction Using Myers-Briggs Kind Indicator and Machine Learning Approaches

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Janvi Bhanushali,
  • Nidhi Goswami,
  • Nirav Bhatt,
  • V. Spoorthy

摘要

In modern psychology, personality exploration is pivotal, with the Myers-Briggs Type Indicator (MBTI) being a widely recognized tool. It categorizes individuals into 16 distinct personality types, providing insights into human behavior. The field has evolved with the rise of personality computing, where digital, data-driven approaches enhance personality assessments’ accuracy. By leveraging text classification algorithms, researchers can analyze extensive digital data, surpassing the limitations of traditional assessments. This fusion of machine learning and personality research marks a significant advancement, offering deeper insights into human behavior. We tested many models: Naïve Bayes, logistic regression (LR), random forest (RF), K-nearest neighbors (KNN), stochastic gradient descent (SGD), and support vector classifier (SVC). LR and SGD were proved to have relatively high precision on introversion/extroversion and intuition/sensing dimensions. RF excelled in the judging/perceiving dimension, achieving perfect accuracy, highlighting the variability in model performance across personality traits. These findings underscore the potential for refined personality insights.