Personality Prediction from Life Stories using Language Models

2025-06-23

AI Summary

This study addresses the automated prediction of Five-Factor Model (FFM) personality traits from lengthy narrative interviews (averaging >2,000 words), overcoming the ecological validity limitations of conventional self-report inventories. We propose a two-stage hybrid modeling framework: first, context-aware fine-tuning of pre-trained language models (e.g., LLaMA, Longformer) via sliding windows to generate fine-grained semantic embeddings; second, an attention-augmented RNN to capture temporal dependencies among personality cues across interview segments. By synergistically integrating pre-trained representation learning with sequential modeling, our approach significantly outperforms baseline methods in prediction accuracy, inference efficiency, and feature interpretability. To our knowledge, this is the first work to systematically demonstrate the efficacy of long-context language modeling for structured personality trait prediction.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Natural Language Processing (NLP) offers new avenues for personality assessment by leveraging rich, open-ended text, moving beyond traditional questionnaires. In this study, we address the challenge of modeling long narrative interview where each exceeds 2000 tokens so as to predict Five-Factor Model (FFM) personality traits. We propose a two-step approach: first, we extract contextual embeddings using sliding-window fine-tuning of pretrained language models; then, we apply Recurrent Neural Networks (RNNs) with attention mechanisms to integrate long-range dependencies and enhance interpretability. This hybrid method effectively bridges the strengths of pretrained transformers and sequence modeling to handle long-context data. Through ablation studies and comparisons with state-of-the-art long-context models such as LLaMA and Longformer, we demonstrate improvements in prediction accuracy, efficiency, and interpretability. Our results highlight the potential of combining language-based features with long-context modeling to advance personality assessment from life narratives.

Problem

• Predicting personality traits from long life stories
• Handling narratives exceeding 2000 tokens effectively
• Improving accuracy and interpretability in personality assessment

Innovation

• Sliding-window fine-tuning for contextual embeddings
• RNNs with attention for long-range dependencies
• Hybrid transformers and sequence modeling approach