Personality Prediction from Life Stories using Language Models
This work addresses personality assessment for psychology and NLP researchers by advancing methods for long-context text analysis, though it is incremental as it builds on existing techniques.
The study tackled predicting Five-Factor Model personality traits from long life story narratives exceeding 2000 tokens by proposing a two-step hybrid method combining sliding-window fine-tuning of pretrained language models with RNNs and attention, resulting in improvements in accuracy, efficiency, and interpretability compared to state-of-the-art models like LLaMA and Longformer.
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.