基于苏格拉底式AI物理导师的学生话语自下而上分类学
A bottom-up taxonomy of student discourse with a Socratic AI physics tutor
浏览论文内容
中文总结 AI 辅助
本研究针对苏格拉底式AI物理导师，构建学生话语自下而上分类学，明确其分布特征，为物理教育研究提供学生与该类AI导师互动的话语参考
中文摘要 AI 辅助
大型语言模型（LLM）导师正被大规模应用于入门物理课程，产生的对话语料库远超传统定性编码可处理的规模。物理教育研究（PER）的核心问题是实证性的，且先于任何有效性主张：学生实际会对这些导师说什么？针对一门基于微积分的力学入门课程中部署的某款苏格拉底式AI导师，我们通过构建学生话语的自下而上分类学来解决该问题。每个学生的对话轮次由LLM编码员利用周围对话语境分配一个新兴自由文本标签；随后使用基于相似度的分组程序，将近义释义标签合并为更少的话语类别。该程序通过分层人类编码样本进行验证。最终得到的357个类别的分类学呈现出惊人的集中性：前25个类别覆盖了约一半的学生对话轮次，且两个主题带——方程处理和元程序请求共同主导了分布的头部。实质性贡献是该分类学本身：它描述了当学生使用这种设计的AI导师时，PER研究人员可预期遇到的话语，包括学生将战略控制权让渡给导师的元程序轮次的惊人普遍性。
英文摘要
Large language model (LLM) tutors are being deployed in introductory physics courses at a scale that produces transcript corpora far larger than traditional qualitative coding can absorb. A central question for physics education research (PER) is empirical and prior to any claim about effectiveness: what do students actually say to these tutors? We address this question for one Socratic AI tutor deployed in an introductory calculus-based mechanics course by building a bottom-up taxonomy of student discourse. Each student turn is assigned an emergent free-text label by an LLM coder using the surrounding conversational context; near-paraphrase labels are then consolidated into a smaller set of discourse categories using a similarity-based grouping procedure. The procedure is validated against a stratified human-coded sample. The resulting taxonomy of 357 categories is strikingly concentrated: the top 25 categories cover roughly half of all student turns, and two thematic bands: equation-handling and meta-procedural requests together dominate the head of the distribution. The substantive contribution is the taxonomy itself: a description of the discourse PER researchers can expect to encounter when students work with an AI tutor of this design, including a striking prevalence of meta-procedural turns in which students cede strategic control to the tutor
