A psychological framework for robotic personality

This study introduces a novel approach to enhance human-robot interaction through robotic personalities. Based on the Big Five factor model, a taxonomy model is presented to synthesize personalities. The core of this framework leverages a Bidirectional Encoder Representations from Transformers (BERT) model, enabling tailored behaviors for each person- ality trait. Empirical validation uses a pilot experiment with participants interacting with a robot that embodies different personalities. Questionnaire analysis confirms the framework’s effective creation of well-perceived personality dimensions.