认知诊断模型从学习者的认知结构出发,建模学习者与试题之间的潜在关系,结合智能算法并根据试题作答结果可评估学习者的知识水平.大多数认知诊断模型是将学习者的高阶能力特征视为单维,忽视了后天努力的影响.为此,本文提出了一种考虑能...认知诊断模型从学习者的认知结构出发,建模学习者与试题之间的潜在关系,结合智能算法并根据试题作答结果可评估学习者的知识水平.大多数认知诊断模型是将学习者的高阶能力特征视为单维,忽视了后天努力的影响.为此,本文提出了一种考虑能力特征与努力特征相互补偿的具有二维高阶特征的新认知诊断模型——认知反应模型(Cognitive and Response Model,C&RM).该模型通过设置能力特征与努力特征相互补偿机制来融合两高阶特征参数以精准建模学习者的知识水平.同时,还构建了知识点弱项特征参数,以综合考虑学习者的知识水平与不同知识点对作答试题的影响,进一步提高模型的解释性和预测精度.采用自建的HNU_SYS数据集和Math1,Math2,FrcSub公共数据集,通过实验对比分析了C&RM模型、最新的认知诊断模型和经典诊断模型.当数据训练集为70%最佳比例时,C&RM在4个数据集上分别比次优方法提升了6.3%,4.3%,3.3%,5.2%,其预测性能最佳,验证了本文模型的可行性和有效性.展开更多
Cognitive diagnosis is an important issue of intelligent education systems,which aims to estimate students'proficiency on specific knowledge concepts.Most existing studies rely on the assumption of static student ...Cognitive diagnosis is an important issue of intelligent education systems,which aims to estimate students'proficiency on specific knowledge concepts.Most existing studies rely on the assumption of static student states and ig-nore the dynamics of proficiency in the learning process,which makes them unsuitable for online learning scenarios.In this paper,we propose a unified temporal item response theory(UTIRT)framework,incorporating temporality and random-ness of proficiency evolving to get both accurate and interpretable diagnosis results.Specifically,we hypothesize that stu-dents'proficiency varies as a Wiener process and describe a probabilistic graphical model in UTIRT to consider temporali-ty and randomness factors.Furthermore,based on the relationship between student states and exercising answers,we hy-pothesize that the answering result at time k contributes most to inferring a student's proficiency at time k,which also re-flects the temporality aspect and enables us to get analytical maximization(M-step)in the expectation maximization(EM)algorithm when estimating model parameters.Our UTIRT is a framework containing unified training and inferenc-ing methods,and is general to cover several typical traditional models such as Item Response Theory(IRT),multidimen-sional IRT(MIRT),and temporal IRT(TIRT).Extensive experimental results on real-world datasets show the effective-ness of UTIRT and prove its superiority in leveraging temporality theoretically and practically over TIRT.展开更多
当前国内外开发的认知诊断模型基本上只能处理单策略的测验情景,并假设所有被试均采用同一种加工策略/解题策略,从而忽视了加工策略的多样性及差异性。本研究根据de la Torre和Douglas(2008)采用多个Q矩阵来表征多个加工策略的思想,并...当前国内外开发的认知诊断模型基本上只能处理单策略的测验情景,并假设所有被试均采用同一种加工策略/解题策略,从而忽视了加工策略的多样性及差异性。本研究根据de la Torre和Douglas(2008)采用多个Q矩阵来表征多个加工策略的思想,并结合使用丁树良等(2009)修正的Q矩阵理论及孙佳楠,张淑梅、辛涛和包珏(2011)的广义距离判别法,开发了一种新的多策略认知诊断方法——MSCD方法。Monte Carlo模拟研究结果表明:在单策略测验情景下,传统的单策略认知诊断方法与采用MSCD方法的诊断正确率均比较理想,且差异不大;但在多策略测验情景时,传统的单策略认知诊断方法诊断正确率较低,而MSCD方法的诊断正确率却仍较理想;当加工策略增至5种时,MSCD方法仍有较高的边际判准率、模式判准率以及加工策略判准率。研究表明MSCD方法基本合理、可行。这为实现对加工策略的诊断提供了方法学支持,有利于拓展认知诊断在实际中的应用。展开更多
文摘认知诊断模型从学习者的认知结构出发,建模学习者与试题之间的潜在关系,结合智能算法并根据试题作答结果可评估学习者的知识水平.大多数认知诊断模型是将学习者的高阶能力特征视为单维,忽视了后天努力的影响.为此,本文提出了一种考虑能力特征与努力特征相互补偿的具有二维高阶特征的新认知诊断模型——认知反应模型(Cognitive and Response Model,C&RM).该模型通过设置能力特征与努力特征相互补偿机制来融合两高阶特征参数以精准建模学习者的知识水平.同时,还构建了知识点弱项特征参数,以综合考虑学习者的知识水平与不同知识点对作答试题的影响,进一步提高模型的解释性和预测精度.采用自建的HNU_SYS数据集和Math1,Math2,FrcSub公共数据集,通过实验对比分析了C&RM模型、最新的认知诊断模型和经典诊断模型.当数据训练集为70%最佳比例时,C&RM在4个数据集上分别比次优方法提升了6.3%,4.3%,3.3%,5.2%,其预测性能最佳,验证了本文模型的可行性和有效性.
基金supported by the National Key Research and Development Program of China under Grant No.2021YFF0901003the National Natural Science Foundation of China under Grant Nos.U20A20229,61922073,and 62106244the Natural Science Foundation of Anhui Province of China under Grant No.2108085QF272.
文摘Cognitive diagnosis is an important issue of intelligent education systems,which aims to estimate students'proficiency on specific knowledge concepts.Most existing studies rely on the assumption of static student states and ig-nore the dynamics of proficiency in the learning process,which makes them unsuitable for online learning scenarios.In this paper,we propose a unified temporal item response theory(UTIRT)framework,incorporating temporality and random-ness of proficiency evolving to get both accurate and interpretable diagnosis results.Specifically,we hypothesize that stu-dents'proficiency varies as a Wiener process and describe a probabilistic graphical model in UTIRT to consider temporali-ty and randomness factors.Furthermore,based on the relationship between student states and exercising answers,we hy-pothesize that the answering result at time k contributes most to inferring a student's proficiency at time k,which also re-flects the temporality aspect and enables us to get analytical maximization(M-step)in the expectation maximization(EM)algorithm when estimating model parameters.Our UTIRT is a framework containing unified training and inferenc-ing methods,and is general to cover several typical traditional models such as Item Response Theory(IRT),multidimen-sional IRT(MIRT),and temporal IRT(TIRT).Extensive experimental results on real-world datasets show the effective-ness of UTIRT and prove its superiority in leveraging temporality theoretically and practically over TIRT.
文摘当前国内外开发的认知诊断模型基本上只能处理单策略的测验情景,并假设所有被试均采用同一种加工策略/解题策略,从而忽视了加工策略的多样性及差异性。本研究根据de la Torre和Douglas(2008)采用多个Q矩阵来表征多个加工策略的思想,并结合使用丁树良等(2009)修正的Q矩阵理论及孙佳楠,张淑梅、辛涛和包珏(2011)的广义距离判别法,开发了一种新的多策略认知诊断方法——MSCD方法。Monte Carlo模拟研究结果表明:在单策略测验情景下,传统的单策略认知诊断方法与采用MSCD方法的诊断正确率均比较理想,且差异不大;但在多策略测验情景时,传统的单策略认知诊断方法诊断正确率较低,而MSCD方法的诊断正确率却仍较理想;当加工策略增至5种时,MSCD方法仍有较高的边际判准率、模式判准率以及加工策略判准率。研究表明MSCD方法基本合理、可行。这为实现对加工策略的诊断提供了方法学支持,有利于拓展认知诊断在实际中的应用。
