The constructive process of knowledge acquisition: Student modeling

  • Hans Spada
  • Michael Stumpf
  • Klaus Opwis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 360)


Despite some optimistic claims of the contrary it is still in the distant future to teach by means of truly self-adapting systems. Nevertheless, one main focus of Cognitive Science lies on this issue of how to construct a system which has the special feature to adjust its behavior to the student/user in a sophisticated way. One answer is student modeling. Findings of Cognitive Psychology and tools of Artificial Intelligence are combined to assess the student's knowledge and the learning process she is subject to, while working with the system. We discuss several approaches towards student modeling namely overlay models, enumerative diagnosis systems, and generative models based on theories of knowledge acquisition.

To address these topics, we have developed the AI-based microworld DiBi (disk billiard) and FEDS, a flat enumerative diagnosis system. Both systems are implemented on XEROX 11xx/SIEMENS 58xx machines running InterLISP-D and PRISM.

DiBi is a computerized learning environment for elastic impacts as a subtopic of classical mechanics. The student learns by designing experiments, making predictions about their outcomes and by revising her hypotheses based on a comparison of her predictions with the computer-generated feedback. The constructive process of knowledge acquisition can be understood as experience-based learning.

A form of passive adaptation to the student can be seen as realized in two aspects of DiBi: Having all characteristics of a microworld, the system enables the student to access optimally fitting information in a self-guided way. In addition, DiBi supports quantitative and qualitative thinking in several ways.

Active adaptation presupposes some kind of student modeling. By means of FEDS, correct quantitative domain-specific knowledge, but also qualitative knowledge and misconceptions are assessed in form of correct, fragmentary and faulty hypotheses. We are working on an improved diagnosis system which is explicitly based on elements of a theory of knowledge acquisition. As a consequence, we will represent the domain in a way which facilitates knowledge communication between system and student in all phases of the learning process. The long-term objective is to develop a really self-adapting teaching system.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bobrow, D.G. (Ed.) (1985). Qualitative reasoning about physical systems. Cambridge, MA: MIT Press.Google Scholar
  2. Brown, J.S. & Burton, R.R. (1978). Diagnostic models for procedural bugs in basic mathematical skills. Cognitive Science, 2, 155–191.CrossRefGoogle Scholar
  3. Brown, J.S. & VanLehn, K. (1980). Repair theory: a generative theory of bugs in procedural skills. Cognitive Science, 4, 379–426.CrossRefGoogle Scholar
  4. Burton, R.R. (1982). Diagnosing bugs in a simple procedural skill. In D.H. Sleeman & J.S. Brown (Eds.), Intelligent Tutoring Systems (pp. 157–184). London: Academic Press.Google Scholar
  5. Carr, B. & Goldstein, J.P. (1977). Overlays: a theory of modeling for computer-aided instruction. AI Lab Memo 406 (Logo Memo 40). Cambridge, MA: MIT.Google Scholar
  6. Di Sessa, A. (1982). Unlearning Aristotelian physics: a study of knowledge-based learning. Cognitive Science, 6, 37–75.CrossRefGoogle Scholar
  7. Falkenhainer, B.C. & Michalski, R.S. (1986). Integrating quantitative and qualitative discovery. The ABACUS system. Machine Learning, 1, 367–402.Google Scholar
  8. Holland, J., Holyoak, K., Nisbett, R.E. & Thagard, P. (1987). Induction: processes of inference, learning and discovery. Cambridge, MA: MIT Press.Google Scholar
  9. Hutchins, E.L., Hollan, J.D. & Norman, D.A. (1986). Direct manipulation interfaces. In D.A. Norman & S.W. Draper (Eds.), User centered system design (pp. 87–124). Hillsdale, NJ: Lawrence Erlbaum.Google Scholar
  10. Klahr, D., Langley, P. & Neches, R. (Eds.). (1987). Production system models of learning and development. Cambridge, MA: MIT Press.Google Scholar
  11. Langley, P. (1987). A general theory of discrimination learning. In D. Klahr, P. Langley & R. Neches (Eds.), Production system models of learning and development (pp. 99–161). Cambridge, MA: MIT Press.Google Scholar
  12. Langley, P., Ohlson, S. & Sage, S. (1984). Machine learning approach to student modeling (Technical Report CMU-RI-TR-84-7). Pittsburgh, PA: The Robotics Institute, Carnegie-Mellon University.Google Scholar
  13. Ohlsson, S. & Langley, P. (1984). PRISM: Tutorial, manual, and documentation (Technical Report). Pittsburgh, PA: The Robotics Institute, Carnegie-Mellon University.Google Scholar
  14. Opwis, K. (1988). Produktionssysteme. In H. Mandl & H. Spada (Hrsg.), Wissenspsychologie (S. 74–98). München: Urban & Schwarzenberg.Google Scholar
  15. Opwis, K., Stumpf, M. & Spada, H. (1987) PRISM: Eine Einführung in die Theorie und Anwendung von Produktionssystemen (Research Report No. 39). Freiburg: Psychological Institute.Google Scholar
  16. Plötzner, R. & Opwis, K. (1987). Modeling discrimination learning in a production system framework (Research Report No. 40). Freiburg: Psychological Institute.Google Scholar
  17. Reimann, P. (in press a). Modeling discovery learning processes in a microworld for geometrical optics. Proceedings of the European Summer University on Intelligent Tutoring Systems. Le Mans 1988.Google Scholar
  18. Reimann, P. (in press b). Toward general knowledge diagnosis systems for student and user modeling. In H. Mandl, E. DeCorte, N. Bennett & H.F. Friedrich (Eds.) Learning and instruction. European research in an international context. Vol. II & III. Oxford: Pergamon Press.Google Scholar
  19. Sleeman, D.H. (1982). Infering (mal) rules from pupil's protocols. In Proceedings of the European Conference on Artificial Intelligence. Orsay, 160–164.Google Scholar
  20. Smith, R.B. (1986). The Alternate Reality Kit: an animated environment for creating interactive simulations. Proceedings of the IEEE Computer Society Workshop on Visual Languages. Dallas, 1986, 99–106.Google Scholar
  21. Spada, H. & Reimann, P. (1986). Hypothesis formation in knowledge acquisition: Preparing the ground for an intelligent tutoring system. In F. Klix & H. Hagendorf (Eds.), Human memory and cognitive capabilities (pp. 951–961). Amsterdam: North Holland.Google Scholar
  22. Spada, H. & Reimann, P. (1988). Wissensdiagnostik auf kognitionswissenschaftlicher Basis. Zeitschrift für Differentielle und Diagnostische Psychologie, 3, 183–192.Google Scholar
  23. Stumpf, M., Opwis, K. & Spada, H. (in press). Knowledge acquisition in a microworld for elastic impacts: The DiBi system. Proceedings of the European Summer University on Intelligent Tutoring Systems, Le Mans, 1988.Google Scholar
  24. Stumpf, M., Branskat, S., Herderich, C., Newen, A., Opwis, K., Plötzner, R., Schult, T. & Spada, H. (1988). The graphical user interface of DiBi, a microworld for collision phenomena (Research Report No. 44). Freiburg: Psychological Institute.Google Scholar
  25. VanLehn, K. (1987). Learning one subprocedure per lesson. Artificial Intelligence, 31, 1–40.CrossRefGoogle Scholar
  26. Wenger, E. (1987). Artificial intelligence and tutoring systems. Los Altos, CA: Kaufmann.Google Scholar
  27. White, B.Y. & Horwitz, P. (1987). Thinker tools: enabling children to understand physical laws (Report No. 6470). Cambridge, MA: BBN Laboratories.Google Scholar
  28. Young, R.M. & O'Shea, T. (1981). Errors in children's subtraction. Cognitive Science, 5, 153–177.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1989

Authors and Affiliations

  • Hans Spada
    • 1
  • Michael Stumpf
    • 1
  • Klaus Opwis
    • 1
  1. 1.Psychological InstituteUniversity of FreiburgFreiburg

Personalised recommendations