Strategic Support of Algebraic Expression Writing

  • Mary A. Mark
  • Kenneth R. Koedinger
Conference paper
Part of the CISM International Centre for Mechanical Sciences book series (CISM, volume 407)


The examination of user data as a basis for developing production models of user behavior has been a major focus in the PAT Algebra I Tutor’s development. In recent work, we have investigated relationships between related tasks and the solution strategies displayed by students. To solve a PAT Algebra I problem, students must complete several related arithmetic and algebraic tasks. The sequences in which these tasks are completed suggest problem-solving strategies of students. We have observed a characteristic pattern of students’ success rates on related tasks. We have also observed that students’ success on specific skills (e.g. constructing a symbolic representation) may differ depending on whether students previously carried out related tasks in the same problem (e.g. solving an analogous arithmetic question). This information has important implications for our user model and our modeling approach.


Algebraic Expression Strategy Choice Related Task Solution Path Concrete Case 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Heffernan, N. T., and Koedinger, K. R. (1997). The composition effect in symbolizing: The role of symbol production vs. text comprehension, Proceedings of the Nineteenth Annual Meeting of the Cognitive Science Society. Mahwah, NJ: Erlbaum.Google Scholar
  2. Katz, S., Lesgold, A., Eggan, G., and Gordin, M. (1994). Modeling the student in Sherlock II. In Greer, J. E., and McCalla, G. I., eds., Student Modelling: The Key to Individualized Knowledge-Based Instruction, New York: Springer-Verlag. 99–125.CrossRefGoogle Scholar
  3. Koedinger, K. R., and Anderson, J. R. (1998). Illustrating principled design: The early evolution of a cognitive tutor for algebra symbolization. Interactive Learning Environments, 5, 161–179.CrossRefGoogle Scholar
  4. Koedinger, K. R., Anderson, J. R, Hadley, W. H., and Mark, M. A. (1997). Intelligent tutoring goes to school in the big city. Internationaljournal of Artificial Intelligence in Education, 8, 30–43.Google Scholar
  5. Koedinger, K. R. and Nathan, M. J. The real story behind story problems: Effects of representations on quantitative reasoning. Manuscript submitted for publication.Google Scholar
  6. Koedinger, K. R. and Sueker, E. L. F. (1996). PAT goes to college. In Proceedings of the Second International Conference on the Learning Sciences, Charlottesville, VA: Association for the Advancement of Computing in Education.Google Scholar
  7. Mark, M. A., Koedinger, K. R, and Hadley, W. H. (1998) Elaborating models of algebraic expression writing. In Intelligent Tutoring Systems: 4th International Conference Proceedings (ITS’98). New York: Springer-Verlag.Google Scholar
  8. Mayer, R. E. (1982). Different problem-solving strategies for algebra word and equation problems. Journal of Experimental Psychology: Learning, Memory and Cognition, 8, 448–462.Google Scholar
  9. Siegler, R. S. and Jenkins, E. (1989). How Children Discover New Strategies. Hillsdale, N. J.: Lawrence Erlbaum Associates.Google Scholar
  10. Van Lehn, K., Niu, Z., Siler, S., and Gertner, A. S. (1998) Student modeling from conventional test data: A Bayesian approach without priors. In Intelligent Tutoring Systems: 4th International Conference Proceedings (ITS’98). New York: Springer-Verlag.Google Scholar

Copyright information

© Springer Science+Business Media New York 1999

Authors and Affiliations

  • Mary A. Mark
    • 1
  • Kenneth R. Koedinger
    • 1
  1. 1.School of Computer ScienceCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations