Reducing Student Hint Use by Creating Buggy Messages from Machine Learned Incorrect Processes

  • Douglas Selent
  • Neil Heffernan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8474)


The goal of this research is to improve existing forms of help in tutoring systems by using “Buggy” messages, which are a simple text message specific to the incorrect answer. Buggy messages are created from machine learned incorrect processes based on the student’s incorrect answer. A randomized control trial is run in ASSISTments to determine if the buggy messages were effective.


Buggy Messages Randomized Control Trial Machine Learning 


  1. 1.
    Aleven, V., Koedinger, K.R.: Limitations of student control: Do students know when they need help? In: Gauthier, G., VanLehn, K., Frasson, C. (eds.) ITS 2000. LNCS, vol. 1839, pp. 292–303. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  2. 2.
    Baker, R., Walonoski, J., Heffernan, N., Roll, I., Corbett, A., Koedinger, K.: Why students engage in “gaming the system” behavior in interactive learning environments. Journal of Interactive Learning Research 19(2), 185–224 (2008)Google Scholar
  3. 3.
    Beck, J.E., Chang, K.-m., Mostow, J., Corbett, A.T.: Does help help? Introducing the Bayesian Evaluation and Assessment methodology. In: Woolf, B.P., Aïmeur, E., Nkambou, R., Lajoie, S. (eds.) ITS 2008. LNCS, vol. 5091, pp. 383–394. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  4. 4.
    Brown, J.S., Burton, R.R.: Diagnostic models for procedural bugs in basic mathematical skills. Cognitive Science 2(2), 155–192 (1978)CrossRefGoogle Scholar
  5. 5.
    Sison, R., Shimura, M.: Student modeling and machine learning. International Journal of Artificial Intelligence in Education (IJAIED) 9, 128–158 (1998)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Douglas Selent
    • 1
  • Neil Heffernan
    • 1
  1. 1.Worcester Polytechnic InstituteUSA

Personalised recommendations