为儿童设计更智能的会话代理：来自认知工作分析与手段-目的分析的经验
Designing Smarter Conversational Agents for Kids: Lessons from Cognitive Work and Means-Ends Analyses
AI总结：
本文通过认知工作分析考察巴西儿童使用会话代理的方式，并在1,200个模拟对话中验证结构化提示“配方”可提升交互质量。
摘要：
本文介绍了两项研究，考察巴西儿童（9至11岁）如何将 conversational agents（CAs，会话代理）用于课业、探索和娱乐，以及结构化支架如何增强这些交互。在研究1中，一项为期七周、包含23名参与者（儿童、父母、教师）的在线调查采用访谈、观察和 Cognitive Work Analysis（认知工作分析），绘制儿童的信息处理流程、更有知识者的作用、功能用途、情境目标和交互模式，以为对话树设计提供依据。我们识别出 CA 的三项功能：School、Discovery 和 Entertainment，并推导出反映亲子支持的“配方”支架。在研究2中，我们在1,200个模拟的儿童-CA交流上提示 GPT-4o-mini，将基于结构化提示的对话树配方与非结构化基线进行比较。对可读性、问题数量/深度/多样性以及连贯性的定量评估显示，配方方法带来提升。基于这些发现，我们提出设计建议：支架式对话树、用于个性化情境的儿童专属档案，以及由照护者筛选的内容。我们的贡献包括首次将 CWA 应用于巴西儿童、一个儿童-CA信息流的实证框架，以及用于有效且有支架学习的 LLM 支架“配方”（即结构化提示）。
英文摘要：
This paper presents two studies on how Brazilian children (ages 9--11) use conversational agents (CAs) for schoolwork, discovery, and entertainment, and how structured scaffolds can enhance these interactions. In Study 1, a seven-week online investigation with 23 participants (children, parents, teachers) employed interviews, observations, and Cognitive Work Analysis to map children's information-processing flows, the role of more knowledgeable others, functional uses, contextual goals, and interaction patterns to inform conversation-tree design. We identified three CA functions: School, Discovery, Entertainment, and derived ``recipe'' scaffolds mirroring parent-child support. In Study 2, we prompted GPT-4o-mini on 1,200 simulated child-CA exchanges, comparing conversation-tree recipes based on structured-prompting to an unstructured baseline. Quantitative evaluation of readability, question count/depth/diversity, and coherence revealed gains for the recipe approach. Building on these findings, we offer design recommendations: scaffolded conversation-trees, child-dedicated profiles for personalized context, and caregiver-curated content. Our contributions include the first CWA application with Brazilian children, an empirical framework of child-CA information flows, and an LLM-scaffolding ``recipe'' (i.e., structured-prompting) for effective, scaffolded learning.
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。
