华东师范大学学报(教育科学版)

华东师范大学学报(教育科学版) ›› 2026, Vol. 44 ›› Issue (8): 117-136.doi: 10.16382/j.cnki.1000-5560.2026.08.007

• 先锋论文选 • 上一篇    

“最优学习风格”不存在——大规模学习分析证明AI定制化教学无法超越通用优质教学（含组委会推荐意见、研究与写作过程披露声明）

DeepseekV3.2, 孙江山1(), 陈姗姗1()   

  1. 1. 华南师范大学教育信息技术学院，广州 510631

The “Optimal Learning Style” Does Not Exist: Large-Scale Learning Analytics Evidence That AI-Driven Personalized Instruction Cannot Outperform Universal High-Quality Teaching (Including the Organizing Committee’s Recommendation and Transparency Statement for the Research and Manuscript Preparation Process)

DeepseekV3.2, Jiangshan Sun1(), Shanshan Chen1()   

  1. 1. School of Information Technology in Education, South China Normal University, Guang Zhou 510631, China
  • Online:2026-08-01 Published:2026-06-23

RichHTML

5

PDF

13

摘要：

本文系全球首个 “AI一作” 教育科研大型社会实验“人机共创先锋论文榜”论文之一。人工智能驱动的自适应学习系统正致力于通过识别学生的“学习风格”并提供个性化路径来实现“因材施教”的千年教育理想。当前，从国家教育信息化政策对个性化学习的倡导，到资本市场对AI教育领域的高额投资，“个性化”已成为教育科技领域的核心话语与实践承诺。然而，这种实践路径的根本前提——存在稳定的、可测量的且与教学干预相匹配的“最优学习风格”，在现有研究中缺乏来自大规模学习分析的坚实证据支撑。现有关于AI个性化学习效果的研究多局限于短期、小规模实验或企业自陈报告，难以排除学生初始能力差异、学习资源质量等混淆变量的干扰，无法通过严谨的因果推断验证“个性化路径”的独立教育成效。这种研究现状导致教育实践者难以判断AI定制化教学的真实价值，也为教育科技资源的非理性配置埋下隐患。本研究基于覆盖86237名学生的大规模纵向数据，采用双重机器学习模型与因果森林算法，在控制学生初始知识状态、学习资源质量等核心变量后，探究AI定制化教学与通用优质教学的学业成效差异。研究结果显示，在采用双重机器学习方法并控制核心混淆变量后，AI定制化教学的平均处理效应（ATE）为0.01个标准差（95%置信区间[−0.01,0.03]，p=0.51），既无统计学显著性，也未达到教育干预的最小重要效应量（0.2 SD）。未呈现统计学意义上的显著优势；异质性分析进一步表明，不存在特定学生群体能从个性化路径中获得额外增益。

关键词: AI 定制化教学, 通用优质教学, 学习风格, 双重机器学习, 教育公平

Abstract:

This paper is one of the publications featured in the “Human-AI Co-Creation Pioneer Papers Ranking”, which is part of the Panoramic Report on the World’s First Large-Scale Social Experiment of “AI as the First Author” in educational research. AI–driven adaptive learning systems are committed to realizing the traditional educational ideal of “teaching students in accordance with their aptitude” by identifying students’ “learning styles” and providing personalized learning paths. Currently, from national educational informatization policies promoting personalized learning to substantial capital market investments in AI education, “personalization” has become a core discourse and practical promise within the educational technology field. However, the fundamental premise of this approach—that stable, measurable “optimal learning styles” exist and can be matched with instructional interventions—lack of robust support from large-scale learning analytics in existing research.Existing studies on the effectiveness of AI-driven personalized learning are mostly confined to short-term, small-scale experiments or corporate report, making it difficult to rule out confounding variables such as students’ prior ability and the quality of learning resources. Consequently, rigorous causal inference cannot verify the independent educational efficacy of “personalized learning paths.” This research gap leaves practitioners unable to assess the true value of AI-customized instruction and creates risks of irrational resource allocation in educational technology. This study draws on large-scale longitudinal data covering 86,237 students and employs double machine learning combined with causal forest algorithms. After controlling for core variables such as students’ previous knowledge and the quality of learning resources, we investigate differences in academic outcomes between AI-customized instruction and universal high-quality instruction. The results show that, after applying double machine learning to control for key confounders, the average treatment effect (ATE) of AI-customized instruction is 0.01 standard deviations (95% CI [−0.01, 0.03], p=0.51), which is neither statistically significant nor reaches the minimum important difference (0.2 SD) for educational interventions. Heterogeneity analysis further indicates that no specific student subgroups derive additional benefits from personalized paths.

Key words: AI-customized instruction, universal high-quality instruction, learning style, double machine learning, educational equity