方法对比

	Bayesian Knowledge Tracing	Cognitive Diagnostic Modeling	知识追踪
领域	Education	Education	教育分析
方法族	Machine learning	Latent structure	Machine learning
起源年份	1994	2010	1994
提出者	Albert Corbett & John Anderson	Tatsuoka; DiBello, Roussos & Stout; Junker & Sijtsma; de la Torre	Albert Corbett & John Anderson
类型	Two-state hidden Markov model of latent skill mastery from response sequences	Restricted latent class models for diagnosing mastery of discrete skills	Probabilistic student modeling
开创性文献	Corbett, A. T., & Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4), 253–278.	Rupp, A. A., Templin, J., & Henson, R. A. (2010). Diagnostic Measurement: Theory, Methods, and Applications. Guilford Press. ISBN: 9781606235270	Corbett, A. T., & Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4), 253–278.
别名	BKT, Knowledge Tracing (Corbett-Anderson), Hidden Markov Knowledge Tracing, Skill Mastery Tracing	CDM, Diagnostic Classification Models, DCM, DINA / G-DINA Models	BKT, Bayesian Knowledge Tracing, Deep Knowledge Tracing, Bilgi İzleme
相关	3	4	3
摘要	Bayesian knowledge tracing (BKT) is a model that estimates, after each problem a student attempts, the probability that the student has mastered the underlying skill. Introduced by Corbett and Anderson for intelligent tutoring systems, it is a two-state hidden Markov model: the latent variable is whether the skill is learned or not, and observed correct/incorrect responses update that latent state through Bayesian inference. With just four parameters — initial knowledge, learning, slip, and guess — BKT drives the mastery decisions that tell a tutor when a student can move on.	Cognitive diagnostic models (CDMs), also called diagnostic classification models, are restricted latent class models that report not a single ability score but a profile of which discrete skills or attributes a student has mastered. Each item is linked to the attributes it requires through a Q-matrix, and the model classifies every examinee into one of the possible binary mastery patterns. CDMs answer 'which specific skills does this student lack' rather than 'how much overall ability does this student have,' making them central to fine-grained diagnostic and formative assessment.	Knowledge Tracing (KT) is a student-modeling technique that estimates, at each moment in time, the probability that a learner has mastered a target knowledge component. Introduced by Corbett and Anderson in 1994, the classical Bayesian Knowledge Tracing (BKT) model treats skill acquisition as a two-state Hidden Markov Model driven by four interpretable parameters: prior knowledge, learning rate, slip, and guess. Deep variants (DKT, DKVMN, AKT) later replaced HMMs with recurrent and transformer architectures.