OCC-PAD-OCEAN:An Quantitative Perceptible Modeling of Big Five Personality Based on Computational Affection

Abstract

In the field of human-centred artificial intelligence, there is an increasing focus on the development of AI systems that can be interpreted and quantified from a psychological perspective. This study represents an interdisciplinary fusion of computer science and psychology, with the objective of revolutionising the analysis of personality traits through the application of deep learning techniques. Our research is based on the 'OCC-PAD-OCEAN' approach and employs the robust VGG19 deep learning architecture for the analysis of video data. The error rate of the AI-generated personality prediction is approximately 20% in comparison to the results obtained from the Big Five personality questionnaire. The empirical findings indicate that the predicted values of C (P < 0.001), E (P = 0.005), and A (P = 0.029) dimensions exhibit a significant difference from the measured values (p > 0.05), thereby demonstrating the model's capacity to accurately reflect subtle individual differences within the Big Five traits. It is noteworthy that our analysis revealed minimal gender-related variations (p = 0.611, p = 0.828, p = 0.522, p = 0.696, p = 0.806), yet notable age-related distinctions in traits such as Agreeableness and Neuroticism (p = 0.027 and p = 0.025). The 'OCC-PAD-OCEAN' approach not only overcomes the inherent limitations of traditional questionnaires by providing a more accurate and computationally efficient alternative for psychological evaluations, but also demonstrates the transformative potential of integrating deep learning into psychological analyses.