Advertisement

Learning Bayesian Knowledge Tracing Parameters with a Knowledge Heuristic and Empirical Probabilities

  • William J. Hawkins
  • Neil T. Heffernan
  • Ryan S. J. D. Baker
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8474)

Abstract

Student modeling is an important component of ITS research because it can help guide the behavior of a running tutor and help researchers understand how students learn. Due to its predictive accuracy, interpretability and ability to infer student knowledge, Corbett & Anderson’s Bayesian Knowledge Tracing is one of the most popular student models. However, researchers have discovered problems with some of the most popular methods of fitting it. These problems include: multiple sets of highly dissimilar parameters predicting the data equally well (identifiability), local minima, degenerate parameters, and computational cost during fitting. Some researchers have proposed new fitting procedures to combat these problems, but are more complex and not completely successful at eliminating the problems they set out to prevent. We instead fit parameters by estimating the mostly likely point that each student learned the skill, developing a new method that avoids the above problems while achieving similar predictive accuracy.

Keywords

Bayesian Knowledge Tracing Expectation Maximization Student Modeling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baker, R.S.J.d., Corbett, A.T., Aleven, V.: More Accurate Student Modeling through Contextual Estimation of Slip and Guess Probabilities in Bayesian Knowledge Tracing. In: Woolf, B.P., Aïmeur, E., Nkambou, R., Lajoie, S. (eds.) ITS 2008. LNCS, vol. 5091, pp. 406–415. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  2. 2.
    Baker, R.S.J.d., Corbett, A.T., Gowda, S.M., Wagner, A.Z., MacLaren, B.A., Kauffman, L.R., Mitchell, A.P., Giguere, S.: Contextual Slip and Prediction of Student Performance After Use of an Intelligent Tutor. In: De Bra, P., Kobsa, A., Chin, D. (eds.) UMAP 2010. LNCS, vol. 6075, pp. 52–63. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  3. 3.
    Beck, J.E., Chang, K.-m.: Identifiability: A fundamental problem of student modeling. In: Conati, C., McCoy, K., Paliouras, G. (eds.) UM 2007. LNCS (LNAI), vol. 4511, pp. 137–146. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    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
  5. 5.
    Corbett, A., Anderson, J.: Knowledge Tracing: Modeling the Acquisition of Procedural Knowledge. User Modeling and User-Adapted Interaction 4, 253–278 (1995)CrossRefGoogle Scholar
  6. 6.
  7. 7.
    Feng, M., Heffernan, N.T., Koedinger, K.R.: Addressing the assessment challenge in an Intelligent Tutoring System that tutors as it assesses. User Modeling and User-Adapted Interaction 19, 243–266 (2009)CrossRefGoogle Scholar
  8. 8.
    Gong, Y., Beck, J.E., Heffernan, N.T., Forbes-Summers, E.: The impact of gaming (?) on learning at the fine-grained level. In: Aleven, V., Kay, J., Mostow, J. (eds.) ITS 2010, Part I. LNCS, vol. 6094, pp. 194–203. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Moon, T.K.: The expectation–maximization algorithm. IEEE Signal Process. Mag. 13, 47–60 (1996)CrossRefGoogle Scholar
  10. 10.
    Murphy, K.: The bayes net toolbox for matlab. Computing Science and Statistics 33, 1024–1034 (2001)Google Scholar
  11. 11.
    Pardos, Z.A., Heffernan, N.T.: Modeling individualization in a bayesian networks implementation of knowledge tracing. In: De Bra, P., Kobsa, A., Chin, D. (eds.) UMAP 2010. LNCS, vol. 6075, pp. 255–266. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Pardos, Z.A., Heffernan, N.T.: Navigating the parameter space of Bayesian Knowledge Tracing models: Visualizations of the convergence of the Expectation Maximization algorithm. In: Baker, R.S.J.d., Merceron, A., Pavlik, P.I. (eds.) Proceedings of the 3rd International Conference on Educational Data Mining, pp. 161–170 (2010)Google Scholar
  13. 13.
    Rai, D., Gong, Y., Beck, J.: Using Dirichlet priors to improve model parameter plausibility. In: Barnes, T., Desmarais, M., Romero, C., Ventura, S. (eds.) Proceedings of the 2nd International Conference on Educational Data Mining, pp. 141–150 (2009)Google Scholar
  14. 14.
    Ritter, S., Harris, T.K., Nixon, T., Dickison, D., Murray, R.C.: Reducing the Knowledge Tracing Space. In: Barnes, T., Desmarais, M., Romero, C., Ventura, S. (eds.) Proceedings of the 2nd International Conference on Educational Data Mining, pp. 151–160 (2009)Google Scholar
  15. 15.
    Wang, Y., Beck, J.: Class vs. Student in a Bayesian Network Student Model. In: Lane, H.C., Yacef, K., Mostow, J., Pavlik, P. (eds.) AIED 2013. LNCS, vol. 7926, pp. 151–160. Springer, Heidelberg (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • William J. Hawkins
    • 1
  • Neil T. Heffernan
    • 1
  • Ryan S. J. D. Baker
    • 2
  1. 1.Department of Computer ScienceWorcester Polytechnic InstituteWorcesterUSA
  2. 2.Department of Human DevelopmentTeachers College, Columbia UniversityNew YorkUSA

Personalised recommendations