逻辑与具体
人格
心理学
生成语法
五大性格特征
认知心理学
特质
公制(单位)
定制
收敛有效性
应用心理学
社会心理学
人格评估量表
生成模型
心理测量学
发展心理学
叙述的
定性研究
推论
趋同(经济学)
人工智能
心理健康
匹配(统计)
过程(计算)
概化理论
计算机科学
作者
Aidan G.C. Wright,Whitney R. Ringwald,Colin E. Vize,johannes Christopher Eichstaedt,Mike Angstadt,Aman Taxali,Chandra Sripada
标识
DOI:10.31234/osf.io/4zx2k_v2
摘要
Contemporary personality assessment relies heavily on psychometric scales, which offer efficiency but risk oversimplifying the rich and contextual nature of personality. Recognizing these limitations, this study explores the use of commercially available generative large language models (LLMs), such as ChatGPT, Claude, etc., to assess personality traits from open-ended qualitative narratives. Across two distinct samples and methodologies (spontaneous streams of thought and daily video diaries) we used generative LLMs to score Big-Five personality traits, achieving convergence with self-report measures comparable to or exceeding established benchmarks (e.g., self-other agreement, ecological momentary assessment, bespoke machine-learning models). LLM-generated trait scores also demonstrated predictive validity regarding daily behaviors and mental health outcomes. This LLM-based approach achieved quantitative rigor based on qualitative data and is easily accessible without specialized training. Importantly, our findings also reaffirm the ubiquity of personality expression, in that it is carried in the stream our thoughts and is woven into the fabric of our daily lives. These results encourage broader adoption of generative LLMs for psychological assessment, and—given the new generation of tools—stress the value of idiographic narratives as reliable sources of psychological insight.
科研通智能强力驱动
Strongly Powered by AbleSci AI