Toward Automatic Hint Generation for Logic Proof Tutoring Using Historical Student Data

  • Tiffany Barnes
  • John Stamper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5091)


We have proposed a novel application of Markov decision processes (MDPs), a reinforcement learning technique, to automatically generate hints for an intelligent tutor that learns. We demonstrate the feasibility of this approach by extracting MDPs from four semesters of student solutions in a logic proof tutor, and calculating the probability that we will be able to generate hints at any point in a given problem. Our results indicate that extracted MDPs and our proposed hint-generating functions will be able to provide hints over 80% of the time. Our results also indicate that we can provide valuable tradeoffs between hint specificity and the amount of data used to create an MDP.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    McKendree, J.: Effective Feedback Content for Tutoring Complex Skills. Human-Computer Interaction 5(4), 381–413 (1990)CrossRefGoogle Scholar
  2. 2.
    Murray, T.: Authoring intelligent tutoring systems: An analysis of the state of the art. Intl. J. Artificial Intelligence in Education 10, 98–129 (1999)Google Scholar
  3. 3.
    Mitrovic, A., Koedinger, K., Martin, B.: A comparative analysis of cognitive tutoring and constraint-based modeling. User Modeling, 313–322 (2003)Google Scholar
  4. 4.
    Koedinger, K.R., Aleven, V., Heffernan., T., McLaren, B., Hockenberry, M.: Opening the door to non-programmers: Authoring intelligent tutor behavior by demonstration. In: 7th Intelligent Tutoring Systems Conference, Maceio, Brazil, pp. 162–173 (2004)Google Scholar
  5. 5.
    McLaren, B., Koedinger, K., Schneider, M., Harrer, A., Bollen, L.: Bootstrapping Novice Data: Semi-automated tutor authoring using student log files. In: Lester, J.C., Vicari, R.M., Paraguaçu, F. (eds.) ITS 2004. LNCS, vol. 3220. Springer, Heidelberg (2004)Google Scholar
  6. 6.
    Beck, J., Woolf, B.P., Beal, C.R.: ADVISOR: A Machine Learning Architecture for Intelligent Tutor Construction. In: 7th National Conference on Artificial intelligence, pp. 552–557. AAAI Press / The MIT Press (2000)Google Scholar
  7. 7.
    Merceron, A., Yacef, K.: Educational Data Mining: a Case Study. In: 12th Intl. Conf. on Artificial Intelligence in Education. IOS Press, Amsterdam (2005)Google Scholar
  8. 8.
    Barnes, T., Stamper, J.: Toward the extraction of production rules for solving logic proofs. In: Proc. 13th Intl. Conf. on Artificial Intelligence in Education, Educational Data Mining Workshop, Marina del Rey (2007)Google Scholar
  9. 9.
    Croy, M., Barnes, T., Stamper, J.: Towards an Intelligent Tutoring System for propositional proof construction. In: Brey, P., Briggle, A., Waelbers, K. (eds.) European Computing and Philosophy Conference. IOS Publishers, Amsterdam (2007)Google Scholar
  10. 10.
    Sutton, S., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Tiffany Barnes
    • 1
  • John Stamper
    • 1
  1. 1.Computer Science DepartmentUniversity of North Carolina at CharlotteCharlotteUSA

Personalised recommendations