AI智能测评视域下英语师范生教学设计能力的诊断与干预策略

Diagnosis and Intervention Strategies for Pre-Service English Teachers’ Instructional Design Competency from the Perspective of AI-Driven Assessment

摘要: 本研究基于AI智能测评，构建了英语师范生教学设计能力诊断体系，并通过闭环干预模式验证了其有效性。研究采用准实验设计，将189名师范生随机分为三组：A组(人机协同组，接收AI报告 + 教师解读)、B组(传统教师反馈组)、C组(纯AI反馈组)。结果表明，A组在目标设计、内容选择、活动安排及评价方法四个维度上均取得极其显著的提升(p < 0.001)，其效果显著优于仅接收教师反馈的B组(p > 0.05)和仅接收AI报告的C组。方差分析进一步证实，A组在所有维度上均表现最佳，而C组在目标设计与评价设计上显著优于B组。该模式通过AI提供的客观诊断与教师的支架式引导，有效提升了师范生的教学设计能力，尤其对低起点学生具有良好补偿效应，为AI赋能教师教育提供了实践路径。

Abstract: This study constructs a diagnostic system for the teaching design ability of English student teachers based on AI intelligent assessment and verifies its effectiveness through a closed-loop intervention model. Using a quasi-experimental design, 189 student teachers were randomly assigned to three groups: Group A (human-AI collaboration, receiving AI reports + teacher interpretation), Group B (traditional teacher feedback), and Group C (AI-only feedback). The results show that Group A achieved extremely significant improvements in all four dimensions of teaching design ability (p < 0.001), significantly outperforming Group B (p > 0.05) and Group C. Further ANOVA analysis confirms that Group A performed best across all dimensions, while Group C significantly outperformed Group B in target design and evaluation design. This model effectively enhances student teachers’ teaching design ability by combining objective AI diagnostics with teacher-led scaffolding, particularly benefiting low-achieving students, and provides a practical pathway for AI-empowered teacher education.