Big Five Personality Prediction through Emotion-Conditioned Representations and Learnable Psycholinguistic Mapping

Abstract

Personality traits influence human behavior and social interactions, making their accurate prediction essential across multiple domains. The Big Five Model, a widely recognized framework in psychological science for assessing personality traits, has become the foundation for different computational approaches to personality prediction. In recent years, a growing body of research has highlighted the dynamic interplay between emotions and personality, as individuals navigate diverse emotional experiences that evoke distinct responses and ultimately shape their behavioral patterns. In this work, we present a novel framework that systematically integrates affective information into Pre-trained Language Models for Big Five Personality trait prediction. Our framework leverages text-based embeddings, emotion-conditioned features, and learnable psycholinguistic information that bridges affective dimensions with personality traits. This design preserves established psycholinguistic knowledge while enabling adaptive refinement through data-driven learning. Our experiments showed that our framework outperformed sentence embedding-based methods and Large Language Models across various datasets from different domains, achieving an average F1-score improvement of at least 15% in out-of-domain scenarios.

Resources

Details