A Probabilistic Framework for Temporal Cognitive Diagnosis in Online Learning Systems  

作　　者：刘嘉聿 汪飞 马海平 黄振亚 刘淇 陈恩红 苏喻 Jia-Yu Liu;Fei Wang;Hai-Ping Ma;Zhen-Ya Huang;Qi Liu;En-Hong Chen;Yu Su(School of Data Science,University of Science and Technology of China,Hefei 230026,China;State Key Laboratory of Cognitive Intelligence,Hefei 230088,China;Anhui Province Key Laboratory of Big Data Analysis and Application,University of Science and Technology of China Hefei 230026,China;School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China;Institutes of Physical Science and Information Technology,Anhui University,Hefei 230601,China;School of Computer Science and Artificial Intelligence,Hefei Normal University,Hefei 230061,China)

机构地区：[1]School of Data Science,University of Science and Technology of China,Hefei 230026,China [2]State Key Laboratory of Cognitive Intelligence,Hefei 230088,China [3]Anhui Province Key Laboratory of Big Data Analysis and Application,University of Science and Technology of China Hefei 230026,China [4]School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China [5]Institutes of Physical Science and Information Technology,Anhui University,Hefei 230601,China [6]School of Computer Science and Artificial Intelligence,Hefei Normal University,Hefei 230061,China

出　　处：《Journal of Computer Science & Technology》2023年第6期1203-1222,共20页计算机科学技术学报（英文版）

基　　金：supported by the National Key Research and Development Program of China under Grant No.2021YFF0901003;the National Natural Science Foundation of China under Grant Nos.U20A20229,61922073,and 62106244;the Natural Science Foundation of Anhui Province of China under Grant No.2108085QF272.

摘　　要：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.

关 键 词：cognitive diagnosis probabilistic graphical model item response theory(IRT) stochastic process expectation maximization(EM)algorithm 

分 类 号：TP39[自动化与计算机技术—计算机应用技术] G40[自动化与计算机技术—计算机科学与技术]