首页|期刊导航|桂林电子科技大学学报|基于多维项目反应理论的可解释动态学习评估模型

基于多维项目反应理论的可解释动态学习评估模型OA

Interpretable dynamic learning assessment model based on multidimensional item response theory

中文摘要英文摘要

精确地刻画学生的动态学习行为并输出具有认知解释性的诊断反馈,是学习分析与智能教育评估领域的核心问题.为此,构建了一种基于多维项目反应理论(MIRT)的可解释动态学习评估模型 DK-MIRT.该模型由知识状态表征层、认知建模层以及预测与诊断层三部分构成:前者利用长短期记忆网络(LSTM)学习学生作答序列中的时序依赖,中间层在 MIRT的结构化框架下显示建模题目难度与区分度等认知参数,后者将学生能力向量与题目属性进行多维交互以生成预测结果与诊断依据.通过这种结构化的协同机制,DK-MIRT 在统一框架内同时实现了较高精度预测与可解释认知诊断,使模型不仅具备数据驱动的预测能力,也具备心理测量意义上的透明度与可解释性.实验结果表明,DK-MIRT 在多个真实数据集上具有优于传统深度知识追踪方法的性能,并能在教育实践中支持学习瓶颈识别、个性化练习路径优化以及知识掌握演化呈现等应用,为自适应教育系统提供了一种兼具性能与解释性的动态学习评估工具.

Accurately characterizing students'dynamic learning behaviors and providing cognitively interpretable diagnostic feed-back are two central challenges in learning analytics and intelligent educational assessment.To address these challenges,an inter-pretable dynamic learning assessment model,termed DK-MIRT(Dynamic Knowledge-aware Multidimensional Item Response The-ory),is developed within the framework of multidimensional item response theory(MIRT).The proposed model consists of three functional modules:a knowledge-state representation layer,a cognitive modeling layer,and a prediction-and-diagnosis layer.The first module employs a long short-term memory(LSTM)network to capture temporal dependencies in response sequences;the sec-ond explicitly models item difficulty,discrimination,and other cognitive parameters within a structured MIRT framework;and the third integrates student ability vectors with item attributes through multidimensional interactions to produce both performance pre-dictions and diagnostic evidence.Through this coordinated architecture,DK-MIRT simultaneously achieves high predictive accura-cy and cognitive interpretability,providing not only strong predictive capability but also psychometrically grounded transparency and traceability.Experimental results on multiple real-world datasets demonstrate that DK-MIRT outperforms conventional deep knowledge tracing methods while supporting practical educational applications,including learning bottleneck identification,person-alized practice recommendation,and knowledge mastery visualization.These findings demonstrate that DK-MIRT provides an ef-fective assessment framework that combines high predictive performance with cognitive interpretability for adaptive educational sys-tems.

郭美美;肖刚

韩山师范学院 数学与统计学院,广东 潮州 521041韩山师范学院 数学与统计学院,广东 潮州 521041

信息技术与安全科学

动态知识追踪多维项目反应理论可解释性学习评估深度学习认知诊断

dynamic knowledge tracingmultidimensional item response theoryinterpretable learning assessmentdeep learningcognitive diagnosis

《桂林电子科技大学学报》 2026 (3)

221-229,9

韩山师范学院教育教学改革(HSJG-GK231133)

10.16725/j.1673-808X.2025309

评论