Bayesian Student Modeling

  • Cristina Conati
Part of the Studies in Computational Intelligence book series (SCI, volume 308)

Abstract

Bayesian networks are a formalism for reasoning under uncertainty that has been widely adopted in Artificial Intelligence (AI). Student modeling, i.e., the process of having an ITS build a model of relevant student’s traits/states during interaction, is a task permeated with uncertainty, which naturally calls for probabilistic approaches. In this chapter, I will describe techniques and issues involved in building probabilistic student models based on Bayesian networks and their extensions. I will describe pros and cons of this approach, and discuss examples from existing Intelligent Tutoring Systems that rely on Bayesian student models

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Arroyo, I., Woolf, B.: Inferring learning and attitudes from a Bayesian Network of log file data. In: 12th International Conference on Artificial Intelligence in Education, AIED 2005 (2005)Google Scholar
  2. Bunt, A., Conati, C., Hugget, M., Muldner, K.: On Improving the Effectiveness of Open Learning Environments through Tailored Support for Exploration. In: 10th World Conference of Artificial Intelligence and Education, AIED 2001 (2001)Google Scholar
  3. Buntine, W.: A Guide to the Literature on Learning Probabilistic Networks from Data. IEEE Transactions on Knowledge and Data Engineering 8(2), 195–210 (1996)CrossRefGoogle Scholar
  4. Chi, M.: Self-explaining: The dual processes of generating inference and repairing mental models. In: Glaser, R. (ed.) Advances in instructional psychology: Educational design and cognitive science, vol. (5), pp. 161–238. Lawrence Erlbaum Associates, Mahwah (2000)Google Scholar
  5. Conati, C., Maclaren, H.: Empirically Building and Evaluating a Probabilistic Model of User Affect. Modeling and User-Adapted Interaction 19(3), 267–303 (2009)CrossRefGoogle Scholar
  6. Conati, C., Merten, C.: Eye-Tracking for User Modeling in Exploratory Learning Environments: an Empirical Evaluation. Knowledge Based Systems 20(6), 557–574 (2007)CrossRefGoogle Scholar
  7. Conati, C., Gertner, A., VanLehn, K.: Using Bayesian Networks to Manage Uncertainty in Student Modeling. Journal of User Modeling and User-Adapted Interaction 12(4), 371–417 (2002)MATHCrossRefGoogle Scholar
  8. Conati, C., Merten, C., Muldner, K., Ternes, D.: Exploring Eye Tracking to Increase Bandwidth in User Modeling. In: Ardissono, L., Brna, P., Mitrović, A. (eds.) UM 2005. LNCS (LNAI), vol. 3538, pp. 357–366. Springer, Heidelberg (2005)Google Scholar
  9. Corbett, A.T., Anderson, J.R.: Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction 4(4), 253–278 (1995)CrossRefGoogle Scholar
  10. Costa, P., McRae, R.: Four ways five factors are. Personality and Individual Differences 13, 653–665 (1992)CrossRefGoogle Scholar
  11. Dean, T., Kanazawa, K.: A Model for REasoning About Persistence and Causation. Computational Intelligence 5(3), 142–150 (1989)CrossRefGoogle Scholar
  12. Dempster, A., Laird, N., Rubin, D.: Maximization-likelihood from Incomplete Data via the EM Algorithm. Journal of Royal Statistical Society, Series B (1977)Google Scholar
  13. D’Mello, S., Craig, S., Witherspoon, A., McDaniel, B., Graesser, A.: Automatic detection of learner’s affect from conversational cues. User Modeling and User-Adapted Interaction, 45–80 (2008)Google Scholar
  14. Ferguson, K., Arroyo, Y., Mahadevan, S., Park Woolf, B., Barto, A.: Improving Intelligent Tutoring Systems: Using Expectation Maximization to Learn Student Skill Levels. In: Ikeda, M., Ashley, K.D., Chan, T.-W. (eds.) ITS 2006. LNCS, vol. 4053, pp. 453–462. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  15. Henrion, M.: Some practical issues in constructing belief networks. In: 3rd Conference on Uncertainty in Artificial Intelligence, pp. 161–173 (1989)Google Scholar
  16. Keeney, R.L., von Winterfeldt, D.: Eliciting probabilities from experts in complex technical problems. IEEE Transactions on Engineering Management 38, 191–201 (1991)CrossRefGoogle Scholar
  17. Martin, J., VanLehn, K.: Student assessment using Bayesian nets. International Journal of Human-Computer Studies 42, 575–591 (1995)CrossRefGoogle Scholar
  18. Mayo, M., Mitrovic, T.: Optimising ITS Behaviour with Bayesian Networks and Decision Theory. International Journal of Artificial Intelligence in Education 12, 124–153 (2001)Google Scholar
  19. Mislevy, R.: Probability-based inference in cognitive diagnosis. In: Nichols, P., Chipman, S., Brennan, R. (eds.) Cognitive Diagnostic Assessment, pp. 43–71. Erlbaum, Hillsdale (1995)Google Scholar
  20. Moore, A., Wong, W.: Optimal Reinsertion: A New Search Operator for Accelerated and More Accurate Bayesian Network Structure Learning. In: ICML 2003, pp. 552–559 (2003)Google Scholar
  21. Murray, C., VanLehn, K., Mostov, J.: Looking Ahead to Select Tutorial Actions: A Decision-Theoretic Approach. International Journal of Artificial Intelligence in Education 14(3-4), 235–278 (2004)Google Scholar
  22. Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo (1988)Google Scholar
  23. Reye, J.: Two-phase updating of student models based on dynamic belief networks. In: Goettl, B.P., Halff, H.M., Redfield, C.L., Shute, V.J. (eds.) ITS 1998. LNCS, vol. 1452, pp. 274–283. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  24. Russel, S., Norvig, P.: Artificial Intelligence - A Modern Approach, 3rd edn. Prentice Hall, Englewood Cliffs (2010)Google Scholar
  25. VanLehn, K., Niu, Z.: Bayesian student modeling, user interfaces and feedback: A sensitivity analysis. International Journal of Artificial Intelligence in Education 12, 154–184 (2001)Google Scholar
  26. Zapata-Rivera, D., Greer, J.: Interacting with Inspectable Bayesian Student Models. International Journal of Artificial Intelligence in Education 14(2), 127–163 (2004)Google Scholar
  27. Zhou, X., Conati, C.: Inferring User Goals from Personality and Behavior in a Causal Model of User Affect. In: UI 2003, International Conference on Intelligent User Interfaces, pp. 211–281. ACM Press, New York (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Cristina Conati
    • 1
  1. 1.Department of Computer ScienceUniversity of British ColumbiaVancouver

Personalised recommendations