Cognitive Diagnosis of Students' Test Performance Based on Probability Inference

Cognitive diagnosis is aimed at inferring the degree of cognitive state from observations. This paper considers cognitive diagnosis as an instance of model-based diagnosis, which has been studied in artificial intelligence for many years. The model-based cognitive diagnosis we present runs on a model of students' courses in terms of knowledge items that they may learn, tests them and helps them to understand their faults in cognition, and thus improves their learning performance in an E-learning environment. To do so, courses are formally defined as set of knowledge items with requirement constraints, and associated with a set of exam questions. Moreover, the authors introduce Bayesian net to build a model of cognitive diagnosis, using probabilistic inference on it to help a student understand what knowledge item he/she does not master, and the recommendations like what should be done next. Experimental results show that the group of students with such understanding can improve their testing performance greatly in an E-learning environment. Although the demo system has been integrated with a specific computerized adaptive testing system, the general technique could be applied to a broad class of intelligent tutoring systems.

[1]  Dane K. Peterson,et al.  Strength of Privacy Policy Statements and Consumer Trust , 2008 .

[2]  Stellan Ohlsson,et al.  Some principles of intelligent tutoring , 1986 .

[3]  Jürg Kohlas,et al.  Model-Based Diagnostics and Probabilistic Assumption-Based Reasoning , 1998, Artif. Intell..

[4]  N. Delener,et al.  Service Science Research, Strategy and Innovation: Dynamic Knowledge Management Methods , 2012 .

[5]  Ron Rymon,et al.  Search through Systematic Set Enumeration , 1992, KR.

[6]  Yun Peng,et al.  A Probabilistic Causal Model for Diagnostic Problem Solving Part I: Integrating Symbolic Causal Inference with Numeric Probabilistic Inference , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  Yun Peng,et al.  A Probabilistic Causal Model for Diagnostic Problem Solving Part II: Diagnostic Strategy , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Hua-Hua Chang,et al.  A Simulation Study to Compare CAT Strategies for Cognitive Diagnosis , 2003 .

[9]  Pierre Dillenbourg,et al.  A Framework for Learner Modelling , 1992, Interact. Learn. Environ..

[10]  Mae Keary,et al.  Web Technologies for Commerce and Services Online , 2009 .

[11]  Lars Bollen,et al.  Toward Cognitive Tutoring in a Collaborative, Web-Based Environment , 2004, ICWE Workshops.

[12]  Maria De Marsico,et al.  The Zone of Proximal Development between Adaptive Learning and Reputation-based Group Activities , 2011, DMS.

[13]  Joseph E. Beck,et al.  ADVISOR: A Machine Learning Architecture for Intelligent Tutor Construction , 2000, AAAI/IAAI.

[14]  Arthur C. Graesser,et al.  Using Latent Semantic Analysis to Evaluate the Contributions of Students in AutoTutor , 2000, Interact. Learn. Environ..

[15]  Noel Doherty,et al.  Strategic Marketing: Models and Plans , 2012 .

[16]  Shie-Jue Lee,et al.  Deriving minimal conflict sets by CS-trees with mark set in diagnosis from first principles , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[17]  Markus Stumptner,et al.  Consistency-based diagnosis of configuration knowledge bases , 1999, Artif. Intell..

[18]  Joseph Budu,et al.  International Journal of E-Services and Mobile Applications , 2015 .

[19]  Johan de Kleer,et al.  Using Crude Probability Estimates to Guide Diagnosis , 1990, Artif. Intell..

[20]  David Poole,et al.  Probabilistic Conflicts in a Search Algorithm for Estimating Posterior Probabilities in Bayesian Networks , 1996, Artif. Intell..

[21]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[22]  Alan Huebner,et al.  An Overview of Recent Developments in Cognitive Diagnostic Computer Adaptive Assessments. , 2010 .

[23]  Markus Stumptner,et al.  DiKe - a model-based diagnosis kernel and its application , 2001, AI Commun..

[24]  Carl Adams,et al.  Evolution of Electronic and Mobile Business and Services: Government Support for E/M-Payment Systems , 2010, Int. J. E Serv. Mob. Appl..

[25]  Russell Greiner,et al.  A Correction to the Algorithm in Reiter's Theory of Diagnosis , 1989, Artif. Intell..

[26]  Huang Jie.  A Compounded Genetic and Simulated Annealing Algorithm for Computing Minimal Diagnosis , 2004 .

[27]  Ouyang Dantong,et al.  A method of combining SE-tree to compute all minimal hitting sets , 2006 .

[28]  Dimitra Dodou,et al.  Five-Point Likert Items: t test versus Mann-Whitney-Wilcoxon , 2010 .

[29]  Lin Li.  Computing the Minimal Hitting Sets with Binary HS-Tree , 2002 .

[30]  Jiang Yun.  The Computation of Hitting Sets with Boolean Formulas , 2003 .

[31]  Rong Chen,et al.  Diagnosing Program Errors with Light-Weighted Specifications , 2006, IEA/AIE.

[32]  Raymond Reiter,et al.  A Theory of Diagnosis from First Principles , 1986, Artif. Intell..

[33]  John A. Self,et al.  Model-based cognitive diagnosis , 1993, User Modeling and User-Adapted Interaction.

[34]  Peter J. F. Lucas.  Bayesian model-based diagnosis , 2001, Int. J. Approx. Reason..

[35]  Marco Temperini,et al.  Design and implementation of a logical framework for course configuration in e-learning , 2003 .

[36]  P. Sasikala,et al.  Cloud Computing in Higher Education: Opportunities and Issues , 2011, Int. J. Cloud Appl. Comput..

[37]  Barney Dalgarno,et al.  A conceptual model for game based intelligent tutoring systems , 2007 .

[38]  Peter Lucas,et al.  Conflict-based diagnosis: adding uncertainty to model-based diagnosis , 2007, IJCAI 2007.

[39]  Sunil Vadera,et al.  Any Time Probabilistic Reasoning for Sensor Validation , 1998, UAI.