Newtonian mechanics is a core module in technology courses, but is difficult for many students to learn. Computerized tutoring can assist the teachers to provide individualized instruction. This article presents the application of decision theory to develop a tutoring system, iTutor, to select optimal tutoring actions under uncertainty of students' mastery states. The novelties of this research are: 1) the automation of student diagnosis that is made possible when tutoring alternatives and the utilities for different outcomes are incorporated to the Bayesian network; and 2) the ability of the tutoring system to select test items with difficulties that are appropriate for the students. The results from formative evaluation on iTutor indicate that it is adaptive, working in a well-structured knowledge space, and able to use the information gathered from the student's responses to dynamically modify the presentation in clearly defined ways.
Get full access to this article
View all access options for this article.
References
1.
BeckJ.SternM.HaugsjaaE. (1996). Applications of AI in education. Proceedings of the Third International Conference on Intelligent Tutoring Systems.
2.
BeckJ.SternM.WoolfB. P. (1997, June). Using the student model to control problem difficulty (pp. 277–289). Proceedings of the 6th International Conference on User Modeling, Sardinia, Italy.
BrunerJ. (1992). Science education and teachers: A Karplus lecture. Journal of Science Education and Technology, 1(1), 5–12.
5.
BurnsH. L.CappsC. G. (1988). Foundations of intelligent tutoring systems. In PolsonM. C.RichardsonJ. J. (Eds.), Foundations of intelligent tutoring systems (pp. 55–78). Mahwah, NJ: Lawrence Erlbaum Associates.
6.
CassandraA. R.KaelblingL. P.LittmanM. L. (1994, July-August). Acting optimally in partially observable stochastic domains (pp. 1023–1028). Proceedings of the Twelfth National Conference on Artificial Intelligence, Washington, DC.
7.
ChengJ.DruzdzelM. J. (2000). AIS-BN: An adaptive importance sampling algorithm for evidential reasoning in large Bayesian networks. Journal of Artificial Intelligence Research, 13, 155–188.
8.
ClarianaR. B. (2003). The effectiveness of constructed-response and multiple-choice study tasks in computer aided learning. Journal of Educational Computing Research, 28(4), 395–406.
9.
ConatiC.GertnerA.VanLehnK. (2002). Using Bayesian networks to manage uncertainty in student modeling. User Modeling and User-Adapted Interaction, 12, 371–417.
10.
D'AmbrosioB. (1999). Inference in Bayesian networks. AI Magazine, 20(2), 21–36.
FarB. H.HashimotoA. H. (2000). A computational model for learner's motivation states in individualized tutoring system (pp. 1059–1067). Proceedings 8th International Conference on Computers in Education/International Conference on Computer-Assisted Instruction, Taipei, Taiwan.
13.
GagnèR.BriggsL.WagerW. (1992). Principles of Instructional Design (4th ed.). Fort Worth, TX: HBJ College Publishers.
14.
GaneshanR.JohnsonW. L.ShawE.WoodB. P. (2000, June). Tutoring diagnostic problem solving (pp. 33–42). Proceedings of the 5th International Conference on Intelligent Tutoring Systems, Montrèal, Canada.
15.
GertnerA.VanLehnK. (2000, June). ANDES: A coached problem solving environment for physics (pp. 133–142). Proceedings of the 5th International Conference on Intelligent Tutoring Systems, Montrèal, Canada.
16.
GuvenS.BlandfordA. (1998, April). An adaptive WWW-based educational hypertext system using symbolic machine learning. Proceedings of 3rd Middlesex University Conference on Research in Technology, Middlesex University.
17.
HeckermanD. (1991). Probabilistic similarity networks. Cambridge, MA: MIT Press.
18.
HeckermanD. (1999). A tutorial on learning with Bayesian networks. In JordanM. I. (Ed.), Learning in graphical models (pp. 301–354). Cambridge, MA: MIT Press.
19.
HoltP.DubsS.JonesM.GreerJ. E. (1994). The state of student modeling. In Student modeling: The key to individualized knowledge-based instruction, NATO ASI Series (Vol. 125; pp. 3–35). New York: Springer-Verlag.
20.
HorvitzE.BreeseJ.HenrionM. (1988). Decision theory in expert systems and artificial intelligence. International Journal of Approximate Reasoning2, 247–302.
21.
LiuC. C.ChenG. D.WangC. Y.LuC. F. (2002). Student performance assessment using Bayesian network and Web portfolios. Journal of Educational Computing Research, 27(4), 437–469.
22.
MarkM. A.GreerJ. E. (1993). Evaluation methodologies for intelligent tutoring systems. Journal of Artificial Intelligence in Education, 4(2/3), 129–153.
23.
MayoM.MitrovicA. (2000). Using a probabilistic student model to control problem difficulty. In GauthierG.FrassonC.VanLehnK. (Eds.), Proceedings of 5th International Conference on Intelligent Tutoring Systems (pp. 524–533). New York: Springer-Verlag.
24.
MayoM.MitrovicA. (2001). Optimising ITS behavior with Bayesian networks and decision theory. International Journal of Artificial Intelligence and Education, 12, 124–153.
25.
MayoM.MitrovicA.McKenzieJ. (2000). CAPIT: An intelligent tutoring system for capitalization and punctuation. In KinshukC. JesshopeOkamotoT. (Eds.), Advanced learning technology: Design and development issues (pp. 151–154). Los Alamitos, CA: IEEE Computer Society.
26.
MillánE.Perez-de-la-CruzJ. L. (2002). A Bayesian diagnostic algorithm for student modeling and its evaluation. International Journal of User Modeling and User-Adapted Interaction, 12, 281–330.
27.
MilneS.ShiuE.CookJ. (1996). Development of a model of user attributes and its implementation within an adaptive tutoring system. User Modeling and User-Adapted Interaction, 6, 303–335.
MitrovicA.MartinB.MayoM. (2002). Using evaluation to shape ITS design: Results and experiences with SQL-Tutor. User Modeling and User-Adapted Interaction, 12, 243–279.
30.
MurrayR.VanLehnK. (2000). DT Tutor: A decision-theoretic, dynamic approach for optimal selection of tutoring actions. In GauthierG.FrassonC.VanLehnK. (Eds.), Proceedings of 5th International Conference on Intelligent Tutoring Systems (pp. 153–162). New York: Springer-Verlag.
31.
MurrayR.VanLehnK.MostowJ. (2001). A decision-theoretic architecture for selecting tutorial discourse. Presented at the AI-ED 2001 Workshop on Tutorial Dialogue Systems, San Antonio, TX.
32.
MurrayW. (1998). A practical approach to Bayesian student modeling. In Proceedings of 4th International Conference ITS'98 (pp. 424–433). Berlin Heidelberg: Springer Verlag.
33.
NilsonN. (1998). Artificial intelligence: A new synthesis. San Mateo, CA: Morgan Kaufmann.
34.
Norsys Software Corp. (1999). Netica API Programmer's Library Reference Manual, version 1.06. [Computer software and manual]. Retrieved June 20, 2001. Available online: http://www.norsys.com.
35.
PatzR. J.JunkerB.W. (1997). A straightforward approach to Markov Chain Monte Carlo methods for item response models. Doctoral dissertation, Carnegie Mellon University.
36.
PearlJ. (1988). Probabilistic reasoning in intelligent systems: Networks of plausible inference. San Mateo, CA: Morgan Kaufmann Publishers, Inc.
37.
PekP. K. (2003). Decision-theoretic intelligent tutoring system. Ph.D thesis, National University of Singapore.
38.
PekP. K.PohK. L. (2000a). Framework of a decision-theoretic tutoring system for learning of mechanics. Journal of Science Education & Technology, 9(4), 343–356.
39.
PekP.K.PohK. L. (2000b, November). Using decision networks for adaptive tutoring. In Proceedings of 8th International Conference on Computers in Education/International Conference on Computer-Assisted Instruction (pp. 1076–1084). Taipei, Taiwan.
40.
PekP. K.PohK. L. (2002). Formulation of tutoring policy for maximizing students' learning through decision-theoretic approach. International Journal of Engineering Education, 18(6), 652–666.
41.
ReyeR. (1996). A belief net backbone for student modeling. In Lecture notes in computer science: Vol. 1086 (pp. 596–604). Proceedings of 3rd International Conference of Intelligent Tutoring Systems. Berline Heidelberg: Springer-Verlag.
42.
ReyeJ. (1998). Two-phase updating of student models based on dynamic belief networks. In GoettleB.HalffH.RedfieldC.ShuteV. (Eds.), Proceedings of the 4th International Conference on Intelligent Tutoring Systems (pp. 274–283). New York: Springer-Verlag.
43.
ShaferG. (1986). Probability judgment in artificial intelligence. In KanalL.LemmerJ. (Eds.), Uncertainty in artificial intelligence. New York: North-Holland.
44.
SternM.BeckJ.WoolfB. (1999). Naïve Bayes Classifiers for User Modeling. Massachusetts: Center for Knowledge Communication, Computer Science Department, University of Massachusetts.
45.
Urban-LurainM. (1996). Intelligent tutoring systems, an historic review in the context of the development of artificial intelligence and educational psychology. Technical report, Department of Computer Science and Engineering, Michigan State University. Available online: http://aral.cse.msu.edu/Publications/ITS/its.htm.
46.
VanLehnK. (1988). Student modeling. In PolsonM.RichardsonM. (Eds.), Foundations of intelligent tutoring systems (pp. 55–78). Hillsdale, NJ: Lawrence Erlbaum Associates.
47.
VanLehnK.NiuZ.SilerS.GertnerA. (1998). Student modeling from conventional test data: A Bayesian approach without priors. In GoettleB.HalffH.RedfieldC.ShuteV. (Eds.), Proceedings of the 5th International Conference on Intelligent Tutoring Systems (pp. 434–443). New York: Springer-Verlag.
48.
VanLehnK.OhlssonS.NasonR. (1995). Applications of simulated students: An exploration. Journal of Artificial Intelligence and Education, 5(2), 135–175.
49.
WeberG.SpechtM. (1997). User modeling and adaptive navigation support in WWW-based tutoring systems. Proceedings of 6th International Conference on User Modelling (UM97) (pp. 289–300), Sardinia, Italy:.
50.
ZedehL. (1983). The role of fuzzy logic in the management of uncertainty in expert systems. Fuzzy Sets and Systems, 11, 199–227.
