UNVEILING PERSONALITY PROFILES: A DATA-DRIVEN APPROACH TO BIG FIVE TRAITS, SENTIMENT, AND TEXTUAL SELF-DESCRIPTION
Abstract
This study presents a data-driven framework for understanding personality traits, emotional expression, and self-description using Natural Language Processing (NLP) and psychometric analysis. The research integrates the Big Five Inventory (BFI), sentiment analysis, semantic embeddings, clustering, and regression modeling to investigate behavioral and emotional patterns reflected in textual self-expression. Data was collected through structured survey responses containing personality inventory items, subjective happiness indicators, lifestyle satisfaction measures, and open-ended responses describing self-identity and workplace rewards.
Big Five personality dimensions were computed using standardized psychometric scoring with reverse-coded items. Advanced NLP techniques, including Sentence Transformers, emotion classification, and zero-shot classification, were employed to analyze textual responses. Additionally, K-Means clustering and UMAP dimensionality reduction were applied to identify latent behavioral groups, while regression analysis examined the relationship between personality traits and subjective well-being.
The findings reveal significant associations between personality dimensions and happiness outcomes, demonstrating the effectiveness of combining psychometric frameworks with modern machine learning techniques for behavioral profiling. The study contributes to the fields of computational psychology and behavioral analytics by providing an integrated approach to personality interpretation through textual analysis and artificial intelligence.
Authors
Krishna Pratap Rao, Ramanand Roy, Rampravesh Kumar, Nishant Kumar, Nisha Kumari
Institution
Noida Institute of Engineering & Technology (MCA Institute), Greater Noida, India
Leave A Comment