发表机构
Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出六阶段工作流，利用生成式人工智能为本科数学构建符合WCAG 2.2 AA级标准的可访问交互式可视化，无需编程，经四个工具验证，各阶段需人工验证，适用于师生。
AI 中文摘要
交互式可视化有助于本科数学的概念理解，但构建此类可视化需要大多数教师所缺乏的编程专业知识。本研究采用基于设计的研究方法，开发、部署并评估了一个六阶段工作流（基础阶段、定制阶段、数学深度阶段、应用阶段、可访问性阶段、教学控制阶段），该工作流利用生成式人工智能构建符合WCAG 2.2 AA级标准的可视化内容，无需编程。这六个阶段为每个提示词提供结构，为人工智能的代码生成提供支架，并确定人工验证的应用环节。本研究探讨该结构是否能可靠生成正确且可访问的工具、是否支持反向操作（从已完成的工具反推提示词）与正向操作（从自然语言想法生成工具），以及每个阶段需要何种验证。本研究针对微积分、多变量微积分和微分方程领域部署了四个工具，通过闭式表达式评估数学正确性，通过自动和手动屏幕阅读器测试评估可访问性，并分析了反复出现的错误。结果表明，该结构能生成结构完整的首次尝试工具，但每个阶段仍必须进行人工验证：在进入下一阶段前，必须检查每个输出的数学正确性、可访问性和教学适配性。该工作流与平台无关，可供教师和学生使用。
英文摘要
Interactive visualizations support conceptual understanding in undergraduate mathematics, but building them has required programming expertise most instructors lack. Using a design-based research approach, we develop, deploy, and evaluate a six-phase workflow (Foundation, Customization, Mathematical Depth, Application, Accessibility, Pedagogical Control) that uses generative AI to build WCAG~2.2 Level~AA compliant visualizations without programming. The six phases structure every prompt, scaffold the AI's code generation, and define where human verification is applied. We ask whether the structure reliably yields correct and accessible tools, whether it runs both backward (reverse-engineering prompts from a finished tool) and forward (generating a tool from a plain-language idea), and what verification each phase requires. Across four deployed tools spanning calculus, multivariable calculus, and differential equations, we evaluate mathematical correctness against closed forms, accessibility through automated and manual screen-reader testing, and the errors that recurred. The structure produces structurally complete first-pass tools, but human verification remains mandatory at every phase: each output must be checked for mathematical correctness, accessibility, and pedagogical fit before the next phase begins. The workflow is platform-independent and serves both instructors and students.
