A Comparison of First-Order and Zeroth-Order Induction for Input-Output Agent Modelling

Most student modelling systems seek to develop a model of the internal operation of the cognitive system. In contrast, Input-Output Agent Modelling (IOAM) models an agent in terms of relationships between the inputs and outputs of the cognitive system. Previous IOAM systems have demonstrated high predictive accuracy in the domain of elementary subtraction. These systems use zeroth-order induction. Many of the predicates used, however, represent relations. This suggests that first-order induction might perform well in this domain. This paper reports a study in which zeroth-order and first-order induction engines were used to build models of student subtraction skills. Comparative evaluation shows that zeroth-order induction performs better than first-order in detecting regularities indicating misconceptions while first-order induction leads zeroth-order in detecting regularities indicating correct concepts and inducing a more comprehensible student model. This suggests there exists a trade-off between these factors and that there is still scope for improvement.

[1]  John Seely Brown,et al.  A tutoring and student modelling paradigm for gaming environments , 1976, SIGCSE '76.

[2]  Stellan Ohlsson,et al.  Automated Cognitive Modeling , 1984, AAAI.

[3]  George E. Forsythe,et al.  Computer science and education , 1968, IFIP Congress.

[4]  Mitsuru Ikeda,et al.  Nonmonotonic Model Inference-A Formalization of Student Modeling , 1993, IJCAI.

[5]  J. Ross Quinlan.  Learning First-Order Definitions of Functions , 1996, J. Artif. Intell. Res..

[6]  H. Ulrich Hoppe,et al.  Deductive error diagnosis and inductive error generalization for intelligent tutoring systems , 1994 .

[7]  John Seely Brown,et al.  Diagnostic Models for Procedural Bugs in Basic Mathematical Skills , 1978, Cogn. Sci..

[8]  William Charles Hoppe.  Cognitive modeling and the evolution of the student model in intelligent tutoring systems , 1992 .

[9]  Albert T. Corbett,et al.  Intelligent Tutoring Systems , 1985, Science.

[10]  Kurt VanLehn,et al.  Repair Theory: A Generative Theory of Bugs in Procedural Skills , 1980, Cogn. Sci..

[11]  John Self.  Artificial Intelligence and Human Learning: Intelligent Computer-Aided Instruction , 1988 .

[12]  Richard M. Young,et al.  Errors in Children's Subtraction , 1981, Cogn. Sci..

[13]  Raymond J. Mooney,et al.  Refinement-based student modeling and automated bug library construction , 1996 .

[14]  John R. Anderson,et al.  Student Modeling and Mastery Learning in a Computer-Based Proramming Tutor , 1992, Intelligent Tutoring Systems.

[15]  Carlo Tasso,et al.  Truth maintenance techniques for modelling student's behavior , 1995 .

[16]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[17]  Jaime R. Carbonell,et al.  AI in CAI : An artificial intelligence approach to computer-assisted instruction , 1970 .

[18]  Geoffrey I. Webb,et al.  Comparative evaluation of alternative induction engines for Feature Based Modelling , 1997 .

[19]  Stellan Ohlsson,et al.  Rules and principles in cognitive diagnoses , 1989 .

[20]  Peter Goodyear,et al.  Teaching knowledge and intelligent tutoring , 1991 .

[21]  Ira P. Goldstein,et al.  The genetic graph: a representation for the evolution of procedural knowledge , 1979 .

[22]  P. Langley,et al.  Identifying Solution Paths in Cognitive Diagnosis. , 1985 .

[23]  Joel D. Martin,et al.  Student assessment using Bayesian nets , 1995, Int. J. Hum. Comput. Stud..

[24]  John R. Anderson,et al.  Cognitive Modeling and Intelligent Tutoring , 1990, Artif. Intell..

[25]  J. R. Quinlan.  Learning Logical Definitions from Relations , 1990 .