| Summary, etc. |
This study presents an innovative approach to predicting personality traits by utilizing<br/>Human-Robot Interaction (HRI). The research focuses on predicting personality traits<br/>based on the Big Five model. The study incorporates nonverbal cues, such as facial<br/>expressions and body language, along with verbal interaction, a 44-item Big Five Inventory<br/>(BFI) questionnaire, and expert analysis. To facilitate the interactive session and<br/>personality prediction, a humanoid robot named NAO was employed. The robot interacted<br/>verbally with the participants, and during these interactions, it captured nonverbal cues,<br/>specifically facial expressions (happy, sad, fear, angry, and surprised), head pose (looking<br/>forward, looking up, looking down, looking left, and looking right), and body poses<br/>(standing, akimbo, close arms, open arms, and thinking). For facial expression analysis, the<br/>researchers employed the Face Emotion Recognition Plus (FER+) dataset, which was<br/>trained using Convolution Neural Network (CNN). This module enabled the recognition of<br/>different facial expressions associated with emotions. The head poses module determined<br/>head angles using Euler angles, while the body pose was estimated by calculating the<br/>shoulder and elbow joint angles using the law of cosine. The proposed system was tested<br/>on 16 participants aged between 21-30 years to access traits i.e., extraversion, neuroticism,<br/>agreeableness, openness, and conscientiousness by integrating questionnaire response,<br/>human-robot interaction, and expert analysis. Results of the study indicate a significant<br/>association between the personality predictions made by the robot and the assessments<br/>conducted by psychologists. In all 16 cases, the predicted personalities were consistent with<br/>the expert opinions. This suggests that the extensive utilization of nonverbal cues,<br/>combined with verbal interaction, holds potential for personality prediction using the Big<br/>Five model. Overall, this study demonstrates an innovative approach to personality<br/>prediction, leveraging Human-Robot Interaction and integrating multiple data sources. By<br/>incorporating nonverbal cues alongside verbal interaction and expert analysis, the proposed<br/>architecture shows promise in predicting personality traits based on the Big Five model. |
