学生与ChatGPT交互可视化：为英语作为外语写作教育设计教师仪表盘
Student-ChatGPT Interaction Visible: Designing a Teacher Dashboard for EFL Writing Education
浏览论文内容
中文总结 AI 辅助
该研究设计了用于EFL写作教育的Prompt Analytics Dashboard，可追踪学生与LLM的交互，经教师测试后能降低监控负担并优化干预时机。
中文摘要 AI 辅助
我们为教师推出了提示分析仪表盘（Prompt Analytics Dashboard, PAD），可追踪英语作为外语（EFL）写作课堂中学生与大型语言模型（LLM）的交互。PAD可展示学生与LLM聊天机器人的提示-响应交互及英语作文修改历史，为课堂提供数据驱动的教学与可见性支持。通过与6名EFL教师开展两轮迭代式协同设计，我们提炼出简洁的追踪分类法（滥用信号、目标对齐线索、修改工作量），并实现了三种界面视图（概览、周/结果筛选、带证据片段的下钻分析）。该流程可在班级/群组层面总结潜在滥用与对齐情况，并附加微观解释以减少过度监控。教师反馈显示，此举降低了扫描负担，且干预时机更清晰。
英文摘要
We present a Prompt Analytics Dashboard (PAD) for teachers that can traces student-LLM interactions from EFL writing classes. PAD can show student prompt-response exchanges with LLM chatbot and English essay writing revision histories to support data-informed instruction and visibility in classes. Through two iterative co-design sessions with six EFL instructors, we distilled a compact trace taxonomy (misuse signals, goal-alignment cues, revision effort) and instantiated three interface views (overview, week/outcome filter, drill-down with evidence snippets). This pipeline summarizes potential misuse and alignment at class/cohort levels and attaches micro-explanations to reduce over-surveillance. Instructors reported reduced scanning burden and clearer timing for interventions.
