Illustrating Principled Design: The Early Evolution of a Cognitive Tutor for Algebra Symbolization

This paper provides an illustration of the principled design of an interactive learning environment. It provides a view of the early stages of this process where design, testing, and redesign are most critical. The long term goals of principled design are twofold: (1) to create a system that can be convincingly demonstrated as an effective and practical learning aid and (2) to provide a replicable account of how and why the system is effective. A principled design is one that is both theoretically guided and empirically supported. A principled design is guided by a set of theoretical principles and specific pedagogical hypotheses (Anderson, Corbett, Koedinger & Pelletier, 1995: Koedinger & Anderson, 1993). It is informed by user testing early and often. The design process is iterative: theory, design, test, redesign. Tests that fail lead first to redesign and then. if principled redesigns fail. to changes in the theory. It should be the natural expectation of the field that no Interactive Learning Environment will be fully effective in its initial implementations and that early demonstrations of limitations have a positive. not a negative, bearing on the value of the final system. The only systems immune to some failure are ones that ure never tested. Unfortunately, these are all too common. (For example. Corbett. Koedinger and Anderson (in press) report that only 25% of the papers at recent ITS conferences include any kind of empirical evaluation.) We describe the design of a particular kind of intelligent tutoring system called a cognitive tutor (Anderson, Corbett, Koedinger & Pelletier. 1995). In addition to employing artificial intelligence techniques, cognitive tutors have the defining feature of containing a psychological model of the cognitive processes behind successful and near-successful student performance. This cognitive model provides the core functionality. The cognitive model is used by a

[1]  John R. Anderson,et al.  Student modeling in the ACT Programming Tutor. , 1995 .

[2]  N. Cole Conceptions of Educational Achievement , 1990 .

[3]  K. Koedinger,et al.  PAT Goes to College: Evaluating a Cognitive Tutor for Developmental Mathematics , 1996, ICLS.

[4]  James G. Greeno,et al.  Developmental analysis of understanding language about quantities and of solving problems. , 1988 .

[5]  A. Whitehead The aims of education , 1929 .

[6]  John R. Anderson,et al.  Rules of the Mind , 1993 .

[7]  C. Hirsch Curriculum and Evaluation Standards for School Mathematics , 1988 .

[8]  John R. Anderson The Architecture of Cognition , 1983 .

[9]  John R. Anderson,et al.  Cognitive Tutors: Lessons Learned , 1995 .

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

[11]  W. Kintsch,et al.  The role of understanding in solving word problems , 1988, Cognitive Psychology.

[12]  Clayton Lewis,et al.  Why and How to Learn Why: Analysis-Based Generalization of Procedures , 1988, Cogn. Sci..

[13]  Diane J. Briars,et al.  An integrated model of skill in solving elementary word problems cognition and instruction , 1984 .

[14]  Robert E. Reys,et al.  Solving Verbal Problems: Results and Implications from National Assessment. , 1980 .

[15]  Sol H. Pelavin,et al.  Changing the Odds: Factors Increasing Access to College , 1990 .

[16]  Kenneth R. Koedinger,et al.  Interaction of Deductive and Inductive Reasoning Strategies in Geometry Novices , 1991 .

[17]  Susanne P. Lajoie,et al.  Computers As Cognitive Tools , 2020 .

[18]  H A Simon,et al.  The theory of learning by doing. , 1979, Psychological review.

[19]  John R. Anderson,et al.  Abstract Planning and Perceptual Chunks: Elements of Expertise in Geometry , 1990, Cogn. Sci..

[20]  Keith J Holyoak,et al.  Pragmatic reasoning schemas , 1985, Cognitive Psychology.

[21]  E. Pellicer Anchored Instruction and Its Relationship to Situated Cognition , 1990 .