Machine-Learning Decomposition Identifies a Big Two Structure in Human Personality with Distinct Neurocognitive...

Area of Science:

• Psychology
• Neuroscience
• Machine Learning

Background:

• The Big Five model is the traditional framework in personality neuroscience.
• Existing models explain only partial item-level covariance, suggesting potential for alternative structures.
• The need for a more comprehensive understanding of personality structure and its neural underpinnings is evident.

Purpose of the Study:

• To systematically evaluate personality trait structure across different factor resolutions using a large-scale dataset.
• To identify alternative factor solutions that may complement the Big Five model.
• To establish a neurocognitively grounded framework for understanding personality.

Main Methods:

• Applied an additive and part-based machine learning decomposition.
• Analyzed a mega-scale, global dataset (n = 1,336,840).
• Evaluated trait structure across various factor resolutions.

Main Results:

• Reproduced the canonical Big Five structure.
• Identified a robust Big Two framework: Social Adaptation and Spontaneous Mentation.
• Social Adaptation integrates Extraversion, Agreeableness, and Conscientiousness for external functioning.
• Spontaneous Mentation combines Neuroticism and Openness for internal exploration.
• The Big Two framework improved prediction of functional brain connectivity compared to the Big Five.
• Maintained comparable associations with cognition and mental health outcomes.

Conclusions:

• Established a neurocognitively grounded Big Two framework that complements the Big Five.
• The Big Two offers an interpretable bridge between personality structure, cognitive functioning, and psychopathology.
• This lower-dimensional representation provides enhanced predictive power for brain connectivity.