An Effective Personality Recognition Model Design using Generative Artificial Intelligence based Learning Principles

Abstract

Personality recognition from textual data plays a crucial role in various applications such as social media analysis, recommendation systems, and personalized marketing. In this study, we propose an effective personality recognition model leveraging Generative Artificial Intelligence based Learning Principles (GAILP), which combines DenseNet feature extraction from user profile images with text-based features extracted using Natural Language Processing (NLP) techniques. The model is implemented in Python, utilizing popular libraries such as TensorFlow, Scikit-learn, and NLTK. We evaluate the performance of the proposed model on a Myers-Briggs Personality Type Dataset obtained from Kaggle, containing self-reported MBTI types and associated textual data. Experimental results demonstrate the effectiveness of the GAILP model, achieving an accuracy of over 97% in personality recognition tasks. Our findings highlight the importance of integrating visual and textual cues for accurate personality recognition and underscore the potential of GAILP-based approaches in this domain.