用课程知识图谱分析AI助教对话，发现学生知识盲点。
Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs
- 通过少量样本分类器将学生提问映射到课程知识点
- 80%准确率识别43个知识点，问题量与难度报告显著相关
- 帮助教师定位需加强的教学内容，适合教育数据分析者
大规模在线课程产生数千条学生向对话式AI助教提出的疑问，但这些交互日志仍被闲置为诊断信号。我们提出一个流程：利用基于GPT-4提取的课程概念先修关系图，通过少样本文本分类器将对话中的学生问题映射至课程主题。在164名研究生的AI课程中，对1340个问题事件评估，分类器在43个标签（42个课程主题+1个未知类）上达到80.0%准确率。主题级问题数量与独立中期问卷中学生自评难度显著相关（rho = 0.491, p = 0.008, n = 28主题），提供了一致证据表明分类后的提问流真实反映了主题难度。结果表明，将对话式AI交互日志映射到课程结构，能传递可操作的知识点缺失信号，为教师提供以课程为基础的教学关注视图。
原文摘要 · Abstract (English)
Large online courses generate thousands of student questions directed at conversational AI teaching assistants, yet these interaction logs remain largely untapped as diagnostic signals. We present a pipeline that maps student questions from a conversational AI teaching assistant to curriculum topics using a few-shot text classifier, grounded in a GPT-4-extracted prerequisite knowledge graph of course concepts. Evaluated on 1,340 question events from 164 students in a graduate-level AI course, our classifier achieves 80.0% accuracy across 43 labels (42 curriculum topics plus an "unknown" abstention class). Topic-level question volume correlates significantly with student self-reported difficulty from an independent mid-semester survey (rho = 0.491, p = 0.008, n = 28 topics), providing convergent evidence that the classified question stream reflects genuine topic difficulty. These results demonstrate that conversational AI interaction logs, mapped onto curriculum structure, carry actionable signals about topic-level knowledge gaps and provide instructors with a curriculum-grounded view of which topics warrant attention.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。