从SQL错误到概念缺口：用于个性化反馈的AI驱动知识图谱分析平台
From SQL Errors to Concept Gaps: An AI-Powered Knowledge Graph Analytics Platform for Personalized Feedback
浏览论文内容
中文总结 AI 辅助
该研究提出一款AI驱动知识图谱平台，可关联SQL错误与课程概念缺口，经评估其概念提取有效性达95.7%，三元组正确率达63.8%，能为SQL学习提供个性化诊断反馈。
中文摘要 AI 辅助
这篇创新实践完整论文介绍了一款AI驱动的知识图谱平台，该平台将本科及研究生数据库系统课程中的SQL错误与概念缺口关联起来。学习结构化查询语言（SQL）的学生常受语义错误困扰，这类错误反映的是概念误解而非语法错误；查询可能成功执行却返回错误结果，原因是相关概念存在缺口，例如误用NATURAL JOIN替代显式子查询，体现了对JOIN、GROUP BY和HAVING的交织误解。自动评分系统仅能检测正确性，却无法将错误与课程的概念结构关联，仅提供表层反馈。教育知识图谱研究已证实结构化概念表征对课程分析和自适应学习的价值，但此类方法尚未应用于从学生提交内容中诊断SQL误解。我们提出的平台可自动从教学材料中提取课程概念及关系，通过图数据库将其与学生提交轨迹关联，并在概念层对错误进行分类。我们在两所高校的两门数据库系统课程中对该平台进行评估，其中一门使用真实学生提交内容，另一门使用模拟提交内容，评估方式包括由5名参与者组成的专家研究，以及以大语言模型（LLM）作为评判的自动评估。结果显示，95.7%的提取节点被评为至少具有一定有效性，63.8%的三元组被评为完全正确。专家反馈确认，生成的图谱与教师的心智模型一致，且将错误映射到课程概念可提供可操作的诊断见解；评估其对学生学习的影响仍为未来工作。
英文摘要
This innovative practice full paper describes an AI-powered knowledge graph platform that connects SQL errors to conceptual gaps in undergraduate and graduate database systems courses. Students learning Structured Query Language (SQL) frequently struggle with semantic errors that reflect conceptual misunderstandings rather than syntax mistakes. A query may execute yet return incorrect results due to gaps spanning related concepts; misusing NATURAL JOIN in place of an explicit subquery reflects intertwined misunderstandings of JOIN, GROUP BY, and HAVING. Autograding systems detect correctness but provide surface-level feedback without connecting errors to the conceptual structure of the course. Educational knowledge graph research has shown the value of structured concept representations for curriculum analysis and adaptive learning, but these approaches have not been applied to diagnosing SQL misconceptions from student submissions. We present a platform that automatically extracts course concepts and relations from instructional materials, links them to student submission traces through a graph database, and classifies errors at the concept level. We evaluate the platform across two database systems courses at two universities, one using real student submissions and one using simulated submissions, through an expert study with five participants and an automated evaluation using an LLM as a judge. Results show that 95.7% of extracted nodes were rated as at least somewhat valid and 63.8% of triplets were rated fully correct. Expert feedback confirmed that the generated graphs align with instructor mental models and that mapping errors to course concepts provides actionable diagnostic insight; evaluating impact on student learning remains future work.
