儿童与家长在对话式智能体中想要和感知到了什么?迈向透明、可信、民主化的智能体
What Do Children and Parents Want and Perceive in Conversational Agents? Towards Transparent, Trustworthy, Democratized Agents
AI总结:
本研究调查多国儿童与家长对对话式智能体的信任、伙伴模型及理想设计看法,通过教育研讨会赋能其编程,发现儿童与家长在感知与期望上存在差异,并提出了提升能力、可预测性及信息透明度以培养适当信任的设计启示。
摘要:
从历史上看,研究人员一直侧重于分析WEIRD(西方、受过教育、工业化、富裕且民主)国家的成人对技术的看法。这意味着我们可能没有为儿童以及非WEIRD国家的人群开发合适的技术。在本文中,我们分析了来自多个国家的儿童与家长对一项新兴技术——对话式智能体的看法。我们旨在更好地了解参与者对智能体的信任、伙伴模型,以及他们对“理想未来智能体”的构想,以便研究人员能更好地为这些用户进行设计。此外,我们通过教育研讨会赋能儿童与家长,让他们能够编写自己的智能体程序,并展示了参与者在创建和学习智能体过程中感知的变化。研究(n=49)结果显示:儿童比家长认为智能体更像人类、更温暖且更可靠;参与者比信任家长或朋友更信任智能体能提供正确信息;与家长相比,儿童将其理想智能体描述为比人类更人工;儿童比家长更倾向于关注趣味功能、平易近人/友好的功能以及通过智能体设计解决担忧等问题。我们还讨论了结果对智能体设计的潜在启示,包括设计者如何通过专注于设计智能体的能力和可预测性指标,以及提高智能体信息来源的透明度,来最好地培养对智能体适当的信任水平。
英文摘要:
Historically, researchers have focused on analyzing WEIRD, adult perspectives on technology. This means we may not have technology developed appropriately for children and those from non-WEIRD countries. In this paper, we analyze children and parents from various countries' perspectives on an emerging technology: conversational agents. We aim to better understand participants' trust of agents, partner models, and their ideas of "ideal future agents" such that researchers can better design for these users. Additionally, we empower children and parents to program their own agents through educational workshops, and present changes in perceptions as participants create and learn about agents. Results from the study (n=49) included how children felt agents were significantly more human-like, warm, and dependable than parents did, how participants trusted agents more than parents or friends for correct information, how children described their ideal agents as being more artificial than human-like than parents did, and how children tended to focus more on fun features, approachable/friendly features and addressing concerns through agent design than parents did, among other results. We also discuss potential agent design implications of the results, including how designers may be able to best foster appropriate levels of trust towards agents by focusing on designing agents' competence and predictability indicators, as well as increasing transparency in terms of agents' information sources.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。