知识、理解与信任:个体对人工智能的信任机制  

Knowledge,Understanding and Trust:Mechanisms of Individual Trust in Artificial Intelligence

作　　者：张乐[1,2] 李森林 ZHANG Le;LI Sen-lin

机构地区：[1]山东大学生活质量与公共政策研究中心 [2]山东大学法学院(威海) [3]山东大学政治学与公共管理学院

出　　处：《社会学评论》2023年第3期59-83,共25页Sociological Review of China

基　　金：国家社科基金重点项目“人工智能发展中的社会风险及适应性治理研究”(20ASH009);山东大学人文社科重大项目“防范化解数字化转型中的重大社会风险研究”(21RWZD18)。

摘　　要：我国新一代人工智能发展中的不确定性让其面临着社会信任的挑战。本文的数据分析表明,知识、理解和信任之间确实存在着显著的关系,个体对不同类型知识的掌握程度的差异显著影响了其对人工智能的信任水平,自然科学知识和新技术知识发挥了“因知而信与因懂而信”的促进效应,而人文社会科学知识却没有明显地表现出“因知而疑”的反思功效;个体基于理解所形成的有关人工智能伦理合规性的主观评价则发挥了中介作用。本文为重新认识“公众理解科学”研究范式的价值、回应学界争议提供了理论佐证,也为人工智能相关政策的制定与优化提供了现实参考。The uncertainty in the development of China's new generation of artificial intelligence poses a challenge to its social trust.The data analysis in this article shows that there is indeed a significant relationship and mechanism of influence among knowledge,understanding,and trust.The degree to which individuals grasp different types of knowledge significantly affects their level of trust in artificial intelligence.Natural science knowledge and knowledge of new technology have a promoting effect of"believing based on knowing and understanding".In contrast,knowledge in the humanities and social sciences does not demonstrate a clear reflection effect of"doubting based on knowing".In this process,the subjective evaluation formed by individuals based on their understanding of the ethical compliance of artificial intelligence plays an intermediary role.This study provides theoretical evidence for rethinking the value of the"public understanding of science"paradigm and responding to academic controversies.It also provides a reference for the formulation and optimization of Al-related policies.

关 键 词：人工智能 技术信任 科技伦理 公众理解科学 科学与社会 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] D035[自动化与计算机技术—控制科学与工程]