Artificial intelligence psychological anthropomorphism: scale development and validation

ABSTRACT

This study explores the conceptualization, dimensional structure, and measurement of artificial intelligence (AI) psychological anthropomorphism in service scenarios. Data were collected using semi-structured in-depth interviews. A grounded theory research approach was employed to construct a structural model of AI psychological anthropomorphism that included the dimensions of personality, empathy, and mind. Exploratory and confirmatory factor analyses were subsequently conducted on questionnaire data collected through online surveys and from which a scale for AI psychological anthropomorphism was developed. It consisted of 16 items and demonstrated good reliability and validity. Moreover, using structural equation modeling, strong nomological validity was demonstrated. The results indicate that AI psychological anthropomorphism and its dimensions significantly and positively predict trust and identity threat. These findings enhance understanding of the conceptual meaning and dimensional structure of AI psychological anthropomorphism in service scenarios, as well as provide a psychometrically reliable and valid measurement tool for use in subsequent empirical research. Additionally, the findings offer important insights for AI developers, service providers, and regulatory agencies to ameliorate AI design, formulate AI marketing strategies, and refine AI governance policies.

摘要

本研究旨在系统深入地探讨服务场景中人工智能心理拟人化的概念内涵、维度结构及测量。首先，通过半结构化深度访谈采集数据，运用扎根理论研究方法构建了涵盖性格、共情和心智三个维度的人工智能心理拟人化结构模型。随后，通过对网络调查采集的问卷数据进行探索性和验证性因子分析，开发出一个包含16个题项、信效度俱佳的人工智能心理拟人化测量量表。最后，运用结构方程建模方法进一步验证了该量表的法则效度，结果表明人工智能心理拟人化及其各维度显著正向预测信任和身份威胁。研究结果不仅深化了对服务场景中人工智能心理拟人化概念内涵和维度结构的理解，还为后续实证研究提供了科学可靠的测量工具。此外，研究结果为人工智能开发者、服务提供商和监管机构优化人工智能设计、制定人工智能营销策略和完善人工智能治理政策提供了重要的启示。

KEYWORDS:

• Artificial intelligence
• anthropomorphism
• psychological anthropomorphism
• scale development

关键词:

• 人工智能；拟人化；心理拟人化；量表开发

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by National Natural Science Foundation of China [grant number: 72262016]; Jiangxi Social Science Fund [grant number: 23GL46D]; Ministry of Education Humanities and Social Sciences Research Project [23YJA630132]; Jiangxi Provincial Postgraduate Innovation Special Funds Project [YC2021-B094].