Loading...

Psychological Analysis of Individual's Behavior Based on Artificial Intelligence Methods

Bahrami Bidon, Amir Sina | 2025

66 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 58709 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Hashemi, Matin
  7. Abstract:
  8. Personality traits play a pivotal role in individuals' lives, significantly influencing their choices, social relationships, and performance in both professional and personal environments. Evaluating these traits through traditional methods, such as questionnaires and psychological interviews, is often time-consuming and relies heavily on the precise and honest participation of the subjects. These limitations have prompted researchers to seek modern and more efficient solutions for predicting personality traits. Advancements in deep learning technologies and the emergence of Convolutional Neural Networks (CNNs) have enabled the analysis of facial images and the identification of visual features for personality prediction. Portrait photographs, as a rich source of visual information, can reveal valuable indicators of an individual's personality. Nevertheless, existing methods struggle with challenges such as low accuracy and the requirement for massive datasets. In this research, we have employed an iterative, trial-and-error approach to test several hypotheses aimed at addressing these issues. By building upon the findings of each preceding experiment, we aimed to achieve an optimal level of final accuracy
  9. Keywords:
  10. Deep Learning ; Transfer Learning ; Convolutional Neural Network ; Personality Dimensions ; Big Five Model ; Artificial Intelligence ; Psychoanalysis

 Digital Object List

 Bookmark

No TOC