Exploring a Gamified Personality Assessment Method through Interaction with LLM Agents Embodying Different Personalities
It addresses the need for automated personality assessment in psychology and human-computer interaction, but is incremental as it builds on existing Big Five theory and LLM capabilities.
This study tackled the problem of low-intrusion, automated personality assessment by proposing a gamified framework using LLM agents with different personalities to elicit multifaceted human representations, achieving effective assessments with superior performance in considering personality multiplicity and partially mitigating systematic biases through multi-context aggregation.
The low-intrusion and automated personality assessment is receiving increasing attention in psychology and human-computer interaction fields. This study explores an interactive approach for personality assessment, focusing on the multiplicity of personality representation. We propose a framework of Gamified Personality Assessment through Multi-Personality Representations (Multi-PR GPA). The framework leverages Large Language Models to empower virtual agents with different personalities. These agents elicit multifaceted human personality representations through engaging in interactive games. Drawing upon the multi-type textual data generated throughout the interaction, it achieves personality assessments with interpretable insights. Grounded in the classic Big Five personality theory, we developed a prototype system and conducted a user study to evaluate the efficacy of Multi-PR GPA. The results affirm the effectiveness of our approach in personality assessment and demonstrate its superior performance when considering the multiplicity of personality representation. Error structure analysis further revealed systematic assessment biases in LLMs, which multi-context aggregation partially mitigated.