Advertisement

Self-adjusting curriculum planning in Sherlock II

  • Sandra Katz
  • Alan Lesgold
  • Gary Eggan
  • Maria Gordin
  • Linda Greenberg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 602)

Abstract

What are the main criteria for effective automatic curriculum planning? We propose that there are two criteria-one cognitive, the other motivational: (1) selection of tasks that are at the appropriate difficulty level for the student; i.e., challenging, but not frustrating and (2) enough variety in the chosen tasks to sustain the student's interest. The first objective is the more difficult to meet, because it depends upon the system's ability to adaptively model the student's strengths and weaknesses in the domain being taught. However, student modeling is fraught with uncertainty, brought on by such factors as ambiguity in interpreting student actions, careless errors, forgetting prior knowledge, and insufficient evidence.

We suggest four design principles that can help to make curriculum planning less dependent upon accurate and complete student models: (1) holistic vs. componential instruction, (2) interpretation of student performance relative to expert performance, (3) use of local, rather than global assessment as the criteria for advancement, and (4) letting students have some say in the design of their curriculum. We illustrate these principles by describing the curriculum planner in Sherlock II, an intelligent coached practice environment for electronic fault diagnosis. In addition, we show how task variety can be sustained via the design of the problem set, and by filtering the set of candidate “next” problems according to their distinctive features. Finally, we conclude with some observations about how student input into curriculum planning could be used to update the student model.

Keywords

intelligent tutoring systems student modeling and cognitive diagnosis instructional planning curriculum performance monitoring 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Brown-CD89]
    J. S. Brown, A. Collins, P. Duguid. Situated Cognition and the Culture of Learning, Educational Researcher, Vol. 18, 1989, pp. 32–41.Google Scholar
  2. [Charn91]
    E. Charniak. Bayesian Networks without Tears. AI Magazine. Vol. 12, No. 4, 1991, pp. 50–63.Google Scholar
  3. [Laj-Les90]
    S. P. Lajoie, A. Lesgold. Apprenticeship Training in the Workplace: Computer-Coached Practice Environment as a New Form of Apprenticeship. Machine-Mediated Learning, Vol. 3, 1990, pp. 7–28.Google Scholar
  4. [Les-EKR]
    A. M. Lesgold, A.M., G. Eggan, S. Katz, G. Rao. Possibilities for Assessment Using Computer-Based Apprenticeship Environments. To appear in W. Regian & V. Shute (Eds.), Cognitive Approaches to Automated Instruction. Hillsdale, NJ: Erlbaum.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Sandra Katz
    • 1
  • Alan Lesgold
    • 1
  • Gary Eggan
    • 1
  • Maria Gordin
    • 1
  • Linda Greenberg
    • 1
  1. 1.Learning Research and DevelopmentCenter University of PittsburghPittsburghUSA

Personalised recommendations