Exploring a Gamified Personality Assessment Method through Interaction with LLM Agents Embodying Different Personalities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Baiqiao, Li, Xiangxian, Zhou, Chao, Gai, Xinyu, Liu, Juan, Yang, Xue, Li, Nianlong, Ma, Shuai, Ma, Xiaojuan, Liu, Yong-jin, Bian, Yulong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913006201339904
author Zhang, Baiqiao
Li, Xiangxian
Zhou, Chao
Gai, Xinyu
Liu, Juan
Yang, Xue
Li, Nianlong
Ma, Shuai
Ma, Xiaojuan
Liu, Yong-jin
Bian, Yulong
author_facet Zhang, Baiqiao
Li, Xiangxian
Zhou, Chao
Gai, Xinyu
Liu, Juan
Yang, Xue
Li, Nianlong
Ma, Shuai
Ma, Xiaojuan
Liu, Yong-jin
Bian, Yulong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04005
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring a Gamified Personality Assessment Method through Interaction with LLM Agents Embodying Different Personalities
Zhang, Baiqiao
Li, Xiangxian
Zhou, Chao
Gai, Xinyu
Liu, Juan
Yang, Xue
Li, Nianlong
Ma, Shuai
Ma, Xiaojuan
Liu, Yong-jin
Bian, Yulong
Human-Computer Interaction
Computers and Society
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.
title Exploring a Gamified Personality Assessment Method through Interaction with LLM Agents Embodying Different Personalities
topic Human-Computer Interaction
Computers and Society
url https://arxiv.org/abs/2507.04005