Publications of the Intelligent Computer Tutoring Group

  • Thomson, D., Mitrovic, A. Towards a negotiable student model for constraint-based ITSs. In: Kong, S.C., Ogata, H., Arnseth, H.C., Chan, C.K.K., Hirashima, T., Klett, F., Lee, J.H.M., Liu, C.C., Looi, C.K., Milrad, M., Mitrovic, A., Nakabayashi, K., Wong, S.L., Yang, S.J.H. (Eds.) Proc. 17th Int. Conf. Computers in Education ICCE 2009, Hong Kong: Aspia-Pasicic Society for Computers in Education. (paper # 9)
  • Mathews, M., Mitrovic, A. Does framing a problem-solving scenario influence learning? In: Kong, S.C., Ogata, H., Arnseth, H.C., Chan, C.K.K., Hirashima, T., Klett, F., Lee, J.H.M., Liu, C.C., Looi, C.K., Milrad, M., Mitrovic, A., Nakabayashi, K., Wong, S.L., Yang, S.J.H. (Eds.) Proc. 17th Int. Conf. Computers in Education ICCE 2009, Hong Kong: Aspia-Pasicic Society for Computers in Education (paper # 24)
  • Holland, J., Mitrovic, A., Martin, B. A Constraint-Based Tutor for Java. In: Kong, S.C., Ogata, H., Arnseth, H.C., Chan, C.K.K., Hirashima, T., Klett, F., Lee, J.H.M., Liu, C.C., Looi, C.K., Milrad, M., Mitrovic, A., Nakabayashi, K., Wong, S.L., Yang, S.J.H. (Eds.) Proc. 17th Int. Conf. Computers in Education ICCE 2009, Hong Kong: Aspia-Pasicic Society for Computers in Education (paper #27)
  • Mitrovic, A., Weerasinghe, A. Revisiting Ill-Definedness and Consequences for ITSs. Dimitrova, V., Mizoguchi, R., du Boulay, B., Graesser, A (eds) Proc 14th Int Conf AIED 2009, pp. 375-382.
  • Weerasinghe, A., Mitrovic, A., Martin, B. A preliminary study of a general model for supporting tutorial dialogues. Proc. ICCE 2008, Taiwan, pp. 125-132.
  • Sosnovsky, S., Mitrovic, A., Lee, D., Brusilovsky, P., Yudelson, M. Ontology-based integration of adaptive educational systems. Proc. ICCE 2008, pp. 11-18.
  • Matthews, M., Mitrovic, A., Thomson, D. Analyzing high-level help seeking behaviour in ITSs. W. Nejdl et al. (Eds.): AH 2008, LNCS 5149, pp. 312 - 315, 2008.
  • Mathews, M., Mitrovic, A. Do Students Who See More Concepts in an ITS Learn More? in R.S.J. Baker, T. Barnes and J. Beck (eds), 1st Int. Conference on Educational Data Mining, Montraal, Quebec, Canada, pp. 266-273, 2008.
  • Sosnovsky, S., Mitrovic, A., Lee, D., Brusilovsky, P., Yudelson, M., Brusilovsky, V., & Sharma, D. (2008). Towards integration of adaptive educational systems: mapping domain models to ontologies. In: Dicheva, D., Harrer, A., Mizoguchi, R. (eds.) Proceedings of 6th International Workshop on Ontologies and Semantic Web for E-Learning (SWEL'2008) in conjunction with ITS'2008. Montreal, Canada, June 23, 2008.
  • Mitrovic, A., McGuigan, N., Martin, B. Suraweera, P., Milik, N., Holland, J. Authoring Constraint-based Tutors in ASPIRE: a Case Study of a Capital Investment Tutor ED-MEDIA 2008, Vienna, 30.6.-4.7.2008, pp. 4607-4616.
  • Martin, B., Mitrovic, A. Helping teachers build ITSs with domain schema. B. Woolf et al. (eds) Proc. 9th Int. Conf. ITS 2008, LCNS 5091, Springer-Verlag, pp. 194-203, http://dx.doi.org/10.1007/978-3-540-69132-7_24
  • Barrow, D., Mitrovic, A., Ohlsson, S., Grimley, M. Assessing the impact of positive feedback in constraint-based ITSs. B. Woolf et al. (eds) Proc. 9th Int. Conf. ITS 2008, LCNS 5091, Springer-Verlag, pp. 250-259, 2008. http://dx.doi.org/10.1007/978-3-540-69132-7_29
  • Milik, N., Mitrovic, A., Grimley, M. Investigating the Relationship between Spatial Ability and Feedback Style in ITSs. B. Woolf et al. (eds) Proc. 9th Int. Conf. ITS 2008, LCNS 5091, Springer-Verlag, pp. 281-290, 2008. http://dx.doi.org/10.1007/978-3-540-69132-7_32
  • Zakharov, K., Mitrovic, A., Johnston, L. Towards Emotionally-Intelligent Pedagogical Agents. B. Woolf et al. (eds) Proc. 9th Int. Conf. ITS 2008, LCNS 5091, Springer-Verlag, pp. 19-28, 2008. http://dx.doi.org/10.1007/978-3-540-69132-7_7
  • Mitrovic, A, and the ICTG team. Constraint - based Tutors. Mayers, A., Dufresne, A., Heffernan, N. (eds) Demo Proc. ITS 2008, pp. 29-32.
  • Matthews, M., Mitrovic, A. How does studentsí help-seeking behavior affect learning? B. Woolf et al. (eds) Proc. 9th Int. Conf. ITS 2008, LCNS 5091, Springer-Verlag, pp. 363-372, 2008
  • Ohlsson, S., Mitrovic, A. Fidelity and Efficiency of Knowledge representations for intelligent tutoring systems. TICL, vol. 5, no 2, 101-132, 2007.
  • Mitrovic, A., Martin, B., Suraweera, P. Constraint-based tutors: past, present and future. IEEE Intelligent Systems, special issue on Intelligent Educational Systems, vol. 22, no. 4, pp. 38-45, July/August 2007.
  • Baghaei, N., Mitrovic, A., Irwin, W. Supporting collaborative learning and problem-solving in a constraint-based CSCL environment for UML class diagrams. Accepted for publication in Int. J. Computer-Supported Collaborative Learning.
  • Mitrovic, A., Martin, B. Evaluating the Effect of Open Student Models on Self-Assessment. IJAIED, Special issue on Open Learner Modeling. 17(2), 121-144, 2007.
  • Baghaei, N., Mitrovic, A. From Modelling Domain knowledge to Metacognitive Skills: Extending a Constraint-based Tutoring System to Support Collaboration In C. Conati, K. McCoy and G. Paliouras (eds), 11th Int. Conference on User Modeling, Corfu, Greece, pp. 217-227, 2007.
  • Martin, B., Mitrovic, A., Suraweera, P. Domain modelling with Ontology: A Case Study In A. Cristea and R.M. Carro (eds) Proc of the 5th Int. Workshop on Autoring of Adaptive and Adaptable Hypermedia, at User Modeling 2007, Corfu, Greece, pp. 4-11, 2007. [Awarded best paper]

  • Martin, B., Nicholas, A. Studying Model Ambiguity in a Language ITS In C. Conati, K. McCoy and G. Paliouras (eds), 11th Int. Conference on User Modeling, Corfu, Greece, pp. 425-429, 2007.
  • Zakharov, K., Mitrovic, A., Johnston, L. Pedagogical Agents Trying on a Caring Mentor Role R. Luckin, K. Koedinger, J. Greer (eds) Proc. 13th Int. Conf. Artificial Intelligence in Education AIED 2007, Los Angeles, 2007: 59-66.

  • Nicholas, A., Martin, B. Resolving Ambiguity in German Adjectives. Workshop on AIED Applications in Ill-Defined Domains, at AIED 2007, Los Angeles, USA, 2007.
  • Suraweera, P., Mitrovic, A., Martin, B. Constraint Authoring System: an empirical evaluation R. Luckin, K. Koedinger, J. Greer (eds) Proc. 13th Int. Conf. Artificial Intelligence in Education AIED 2007, Los Angeles, 2007: 451-458.

  • Baghaei, N., Mitrovic, A. Evaluating a Collaborative Constraint-based Tutor for UML class diagrams. R. Luckin, K. Koedinger, J. Greer (eds) Proc. 13th Int. Conf. Artificial Intelligence in Education AIED 2007, Los Angeles, 2007: 533-535.
  • Milik, N., B., Mitrovic, A., Grimley, M. Fitting spatial ability into ITS development. R. Luckin, K. Koedinger, J. Greer (eds) Proc. 13th Int. Conf. Artificial Intelligence in Education AIED 2007, Los Angeles, 2007: 617-619.

  • Weerasinghe, A., Mitrovic, A., Martin, B. Towards a general model of self-explanation to enhance learning. R. Luckin, K. Koedinger, J. Greer (eds) Proc. 13th Int. Conf. Artificial Intelligence in Education AIED 2007, Los Angeles, 2007: 665-667.
  • Mathews, M., Mitrovic, A. (Investigating the Effectiveness of Problem Templates on Learning in Intelligent Tutoring Systems. R. Luckin, K. Koedinger, J. Greer (eds) Proc. 13th Int. Conf. Artificial Intelligence in Education AIED 2007, Los Angeles, 2007: 611-613.

  • Mitrovic, A. and the ICTG team Large-Scale Deployment of three intelligent web-based database tutors. Journal of Computing and Information Technology , vol. 14, no. 4, 275-281, 2006. (Reprinted from V. Luzar, V. Hljuz-Dobric (eds) Proc. ITI 2006, pp. 135-140, Cavtat, Croatia, 19-22.6.2006)

  • Mitrovic, A., Ohlsson, S. Constraint-Based Knowledge Representation for Individualized Instruction Computer Science and Information Systems (COMSIS ), vol 3(1), 1-22, June 2006.

  • Baghaei, N., Mitrovic, A. A Constraint-based Collaborative Environment for Learning UML Class Diagrams. M. Ikeda, K. Ashley, and T.-W. Chan (Eds.): ITS 2006, LNCS 4053, pp. 176-186, 2006. (pdf)

  • Mitrovic, A., Suraweera, P., Martin, B., Zakharov, K., Milik, N., Holland, J. Authoring constraint-based tutors in ASPIRE. M. Ikeda, K. Ashley, and T.-W. Chan (Eds.): ITS 2006, LNCS 4053, pp. 41-50. (pdf)

  • Milik, N., Marshall, M., Mitrovic, A. Teaching Logical Database Design in ERM-Tutor M. Ikeda, K. Ashley, and T.-W. Chan (Eds.): ITS 2006, LNCS 4053, pp. 707-709

  • Weerasinghe, A., Mitrovic, A. Studying human tutors to facilitate self-explanation. M. Ikeda, K. Ashley, and T.-W. Chan (Eds.): ITS 2006, LNCS 4053, pp. 713-715 (poster) (pdf)

  • Weerasinghe, A., Mitrovic, A. Individualizing Self-Explanation Support for Ill-Defined Tasks in Constraint-based Tutors. V. Aleven, K. Ashley, Lynch, C., Pinkwart, N. (eds) ITS 2006 workshop on ITS for Ill-defined domains, pp. 56-64, Jhongli, Taiwan, 26-30.6.2006.
  • Martin, B., Mitrovic, A. The effect of adapting feedback generality in ITS. V. Wade, H. Ashman, and B. Smyth (Eds.): AH 2006, LNCS 4018, pp. 192-202, 2006. (pdf)

  • Mitrovic, A., Ohlsson, S., Martin, B. Problem-solving support in constraint-based tutors Technology, Instruction, Cognition and Learning. †Special issue on Highlights on AERA 2005, vol 3, no 1-2, pp. 43-50, 2006.

  • Baghaei,N., Mitrovic, A., Irvin, W. Problem-Solving Support in a Constraint-based Intelligent Tutoring System for UML Technology, Instruction, Cognition and Learning, vol. 4, no 1-2, 2006.

  • Weerasinghe, A., Mitrovic, A. Facilitating Deep Learning through Self-Explanation in an Open-ended Domain. Int. J. of Knowledge-based and Intelligent Engineering Systems (KES), IOS Press, vol. 10, no 1, 3-19, 2006.

  • Weerasinghe, A., Mitrovic, A. Supporting Deep Learning in an Open-ended Domain. In: M. Negoita, B. Reusch (eds) Real World Applications of Computational Intelligence. New Zealand * German School of Computational Intelligence: Selected Lectures Given at the KES'2004 Conference. Springer-Verlag, Studies in Fuzziness and Soft Computing, Vol. 179, 2005, XVI, 295 p. ISBN: 3-540-25006-9, pp. 105-152.

  • Baghaei, N., Mitrovic, A. COLLECT-UML: Supporting individual and collaborative learning of UML class diagrams in a constraint-based tutor . In: Rajiv Khosla, Robert J. Howlett, Lakhmi C. Jain (eds) Proc. KES 2005, Springer-Verlag, LCNS 3684, pp. 458-464, 2005. (pdf)

  • Weerasinghe, A., Mitrovic, A. Using Affective Learner States to Enhance Learning. In: Rajiv Khosla, Robert J. Howlett, Lakhmi C. Jain (eds) Proc. KES 2005, Springer-Verlag, LCNS 3684, pp. 465-471, 2005. (pdf)

  • Martin, B., Mitrovic, A. Using learning curves to mine student models. In: L. Ardissono, P. Brna, A. Mitrovic (eds) Proc. 10th Int. Conf User Modeling, Springer-Verlag, LNAI 3538, pp. 79-88.

  • Suraweera, P., Mitrovic, A., Martin, B. A knowledge acquisition system for constraint-based intelligent tutoring systems. In: C-K Looi, G. McCalla, B. Bredeweg, J. Breuker (eds) Proc. Artificial Intelligence in Education AIED 2005, IOS Press, pp. 638-645, 2005. ( pdf)

  • Martin, B., Koedinger, K., Mitrovic, A., Mathan, S. On using learning curves to evaluate ITS. In: C-K Looi, G. McCalla, B. Bredeweg, J. Breuker (eds) Proc. Artificial Intelligence in Education AIED 2005, IOS Press, pp. 419-426, 2005. ( pdf)

  • Zakharov, K., Ohlsson, S., Mitrovic, A. Feedback Micro-engineering in EER-Tutor. In: C-K Looi, G. McCalla, B. Bredeweg, J. Breuker (eds) Proc. Artificial Intelligence in Education AIED 2005, IOS Press, pp. 718-725 , 2005. ( pdf)

  • Mitrovic, A. The Effect of Explaining on Learning: a Case Study with a Data Normalization Tutor. In: C-K Looi, G. McCalla, B. Bredeweg, J. Breuker (eds) Proc. Artificial Intelligence in Education AIED 2005, IOS Press, pp. 499-506, 2005. ( pdf)

  • Nilakant, K., Mitrovic, A. Application of data mining in constraint-based intelligent tutoring systems. In: C-K Looi, G. McCalla, B. Bredeweg, J. Breuker (eds) Proc. Artificial Intelligence in Education AIED 2005, IOS Press, pp. 896-898, 2005.
  • Weerasinghe, A., Mitrovic, A. Supporting Self-Explanation in an Open-ended Domain. In: M.Gh.Negoita, R. J. Howlett, L.C. Jain (eds) Proc of the 8th Int. Conf. Knowledge-Based Intelligent Information and Engineering Systems (KES 2004), Wellington, NZ, Sep 20-24, 2004, Berlin: Springer LNAI 3213, pp. 306-313.
  • Mitrovic, A. Scaffolding Answer Explanation in a Data Normalization Tutor. Facta Universitatis, Series Elec. Energ., vol. 18( 2), August 2005, 151-163.

  • Suraweera, P., Mitrovic, A. An Intelligent Tutoring System for Entity Relationship Modeling Int. J. Artificial Intelligence in Education, vol. 14, no. 3-4, 2004, 375-417.

  • Mitrovic, A., Suraweera, P., Martin, B. and Weerasinghe, A. DB-suite: Experiences with Three Intelligent, Web-based Database Tutors . Journal of Interactive Learning Research (JILR), vol. 15, no. 4, pp. 409-432, November 2004.
  • Mitrovic, A., Martin, B. Evaluating adaptive problem selection . In: P. De Bra, W. Nejdl (eds) Proc. 3rd Int. Conf. Adaptive Hypermedia and Adaptive Web-based Systems AH 2004 conference (20% acceptance rate), Eindhoven, 23-26.8.2004, pp. 185-194, Springer-Verlag LNCS 3137, 2004. ( pdf)

  • Martin, B., Mitrovic, A. Evaluating Intelligent Tutoring Systems with Learning Curves . In: Lora Aroyo, Carlo Tasso (eds) Proc. AH 2004 Workshop Proceddings, Part I, Workshop on Empirical Evaluation of Adaptive Systems (http://www.ah2004.org/workshops.html), pp. 179-188, Eindhoven, The Netherlands, 23-26.8.2004.

  • Suraweera, P., Mitrovic, A, Martin, B. The role of domain ontology in knowledge acquisition for ITSs. In: J. Lester, R. M. Vicari and Fabio Paraguacu (eds) Proc. 7th Int. Conf. Intelligent Tutoring Systems ITS 2004, Springer-Verlag LNCS 3220, Maceio, Brazil, pp. 207-216, 2004. ( pdf)

  • Suraweera, P., Mitrovic, A, Martin, B. The use of ontologies in ITS domain knowledge authoring. In: Jack Mostow and Patricia Tedesco (eds), Proc. 2nd Int. Workshop on Applications of Semantic Web for E-learning, ITS 2004 conference (http://wwwis.win.tue.nl/SW-EL04/), pp. 41-49, Maceio, Brazil, 2004.

  • Mitrovic, A. An intelligent SQl tutor on the Web Int. J. Artificial Intelligence in Education, vol. 13, no. 2-4, 2003, 173-197.

  • Mitrovic, A., Koedinger, K., Martin, B. A Comparative Analysis of Cognitive Tutoring and Constraint-Based Modelling . P. Brusilovsky, A. Corbett, F. de Rosis (Eds.) Proceedings of the Ninth International Conference on User Modeling UM 2003, Springer-Verlag, LNAI 2702, 2003, pp. 313-322.

  • Martin, B., Mitrovic, A. Domain Modeling: Art or Science? In: U. Hoppe, F. Verdejo & J. Kay (ed) Proc. 11th Int. Conference on Artificial Intelligence in Education AIED 2003, IOS Press, pp. 183-190, 2003.

  • Weerasinghe, A., Mitrovic, A. Effects of self-explanation in an open-ended domain . In: U. Hoppe, F. Verdejo & J. Kay (ed) Proc. 11th Int. Conference on Artificial Intelligence in Education AIED 2003, IOS Press, pp. 512-514, 2003. ( pdf)

  • Mitrovic, A., Martin, B. Scaffolding and fading problem selection in SQL-Tutor . In: U. Hoppe, F. Verdejo & J. Kay (ed) Proc. 11th Int. Conference on Artificial Intelligence in Education AIED 2003, IOS Press, pp. 479-481, 2003.

  • Mitrovic, A. Supporting Self-Explanation in a Data Normalization Tutor . In: V. Aleven, U. Hopppe, J. Kay, R. Mizoguchi, H. Pain, F. Verdejo, K. Yacef (eds) Supplementary proceedings, AIED 2003, pp. 565-577, 2003.

  • Mitrovic, A., Devedzic, V. A Model of multitutor Ontology-based Learning Environments . Accepted for the Int. J. Continuing Engineering Education and Life-Long Learning. Special issue on ontologies.

  • Mitrovic, A. NORMIT, a Web-enabled tutor for database normalization . In: Kinshuk, R. Lewis, K. Akahori, R. Kemp, T. Okamoto, L. Henderson, C-H Lee (eds) Proc. ICCE 2002, Auckland, 2002, pp. 1276-1280.

  • Martin, B., Mitrovic, A. Authoring Web-Based Tutoring Systems with WETAS. In: Kinshuk, R. Lewis, K. Akahori, R. Kemp, T. Okamoto, L. Henderson, C-H Lee (eds) Proc. ICCE 2002, Auckland, 2002, pp. 183-187.
  • Weerasinghe, A., Mitrovic, A. Enhancing learning through self-explanation. In: Kinshuk, R. Lewis, K. Akahori, R. Kemp, T. Okamoto, L. Henderson, C-H Lee (eds) Proc. ICCE 2002, Auckland, 2002, pp. 244-248.
  • Wang, T., Mitrovic, A. Using neural networks to predict student's behaviour. In: Kinshuk, R. Lewis, K. Akahori, R. Kemp, T. Okamoto, L. Henderson, C-H Lee (eds) Proc. ICCE 2002, 2002, pp. 969-973.
  • Mitrovic, A., Martin, B. & Mayo, M. Using evaluation to shape ITS design: Results and Experiences with SQL-Tutor. Int. J. User Modeling and User-Adapted Interaction, vol. 12, no. 2-3, pp. 243-279, 2002.
  • Hartley, D., Mitrovic, A. Supporting learning by opening the student model. In: S. Cerri, G. Gouarderes and F. Paraguacu (eds.) Proc. 6th Int. Conf on Intelligent Tutoring Systems ITS 2002, Biarritz, France, LCNS 2363, 453-462, 2002.

    Abstract: Intelligent tutoring systems (ITSs) are computer tutors that provide individualised instruction by maintaining models of their students. Traditionally, these models have been hidden from the student. However, recent work in the area has suggested educational benefits in exposing the student model. This approach, known as open student modelling, allows the student to inspect their model thereby facilitating reflection, which is known to enhance the learning process. To date, few evaluations have been conducted to determine the effects that open student models have on learning. This is the focus of our work. In particular, we are interested in whether even a simple open model can have a positive effect on learning. For this purpose, we have exposed the student model in e-KERMIT, and performed an evaluation study. Subjective results from the study are encouraging, although a more extensive study is needed to draw reliable conclusions.


  • Martin, B., Mitrovic, A. Automatic Problem Generation in Constraint-Based Tutors. In: S. Cerri, G. Gouarderes and F. Paraguacu (eds.) Proc. 6th Int. Conf on Intelligent Tutoring Systems ITS 2002, Biarritz, France, LCNS 2363, 388-398, 2002.
  • Suraweera, P., Mitrovic, A. KERMIT: a Constraint-based Tutor for Database Modeling. In: S. Cerri, G. Gouarderes and F. Paraguacu (eds.) Proc. 6th Int. Conf on Intelligent Tutoring Systems ITS 2002, Biarritz, France, LCNS 2363, 377-387, 2002.

    Abstract: KERMIT is an intelligent tutoring system that teaches conceptual database design using the Entity-Relationship data model. Database design is an open-ended task: although there is an outcome defined in abstract terms, there is no procedure to use to find that outcome. So far, constraint based modelling has been used in a tutor that teaches a declarative database language (SQL-Tutor) and a system that teaches punctuation and capitalisation rules in English (CAPIT). Both systems have proved to be extremely effective in evaluations performed in real classrooms. In this paper, we present our experiences in using CBM in an open-ended domain. We describe system's architecture and functionality. KERMIT has also been evaluated in the context of genuine teaching activities. We present the results of an evaluation study with students taking a database course, which show that KERMIT is an effective system. The students enjoyed the system's adaptability and found it a valuable asset to their learning.


  • Mitrovic, A., Martin. B., Evaluating the effect of open student models on learning 2nd Int. Conf. on Adaptive Hypermedia and Adaptive Web-based Systems AH 2002, Malaga, Spain, 29-31 May 2002, pp. 296-305.

    Abstract: In previous work [10], we reported on an experiment performed in the context of SQL-Tutor, in which we analysed students' self-assessment skills. This preliminary study revealed that more able students were better in assessing their knowledge. Here we report on a new study performed on the same system. This time, we analysed the effect of an open student model on students' learning and self-assessment skills. Although we have not seen any significant difference in the post-test scores of the control and the experimental group, the less able students from the experimental group have scored significantly higher than the less able students from the control group. The more able students who had access to their models abandoned significantly less problems the control group. These are encouraging results for a very simple open model used in the study, and we believe that a more elaborate model would be more effective.


  • Mayo, M., Mitrovic, A., Optimising ITS behaviour with Bayesian networks and decision theory , IJAIED, vol. 12, No. 2, pp. 124-153, 2001.
  • Mitrovic, A. Self-assessment: how good are students at it? Proc. Workshop on Assessment Methods in Web-Based Learning Environments & Adaptive Hypermedia, AIED 2001, San Antonio, May 2001, pp. 2-8.
  • Constraint-based tutors: a success story.

    Mitrovic, A., Mayo, M., Suraweera, P and Martin, B. In: L. Monostori, J. Vancza and M. Ali (eds), Proc. 14th Int. Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE-2001, Budapest, June 2001, Springer-Verlag Berlin Heidelberg LNAI 2070, pp. 931-940.

    Abstract: Student modeling (SM) is recognized as one of the central problems in the area of Intelligent Tutoring Systems. Numerous SM approaches have been proposed and used with more or less success. Constraint-based modeling is a new approach, which has been used successfully in three tutors developed in our group. The approach is extremely efficient, and it overcomes many problems that other student modelling approaches suffer from. We present the advantages of CBM over other similar approaches, describe three constraint-based tutors and present our future research plans.


  • Mitrovic, A. Investigating students' self-assessment skills. In: M. Bauer, P.J.Gmytrasiewicz and J. Vassileva (eds) Proc. 8th Int. Conference on User Modeling UM-2001, Sonthofen, July 2001, Springer-Verlag LNAI 2109, pp. 247-250.
  • Mayo, M., Mitrovic, A., McKenzie, J. CAPIT: an Intelligent Tutoring System for Capitalization and Punctuation. International Workshop for Advanced Learning Technologies IWALT2000, December 4-6, 2000, Palmerston North, pp. 151-154.
  • Mitrovic, A., Martin, B. Evaluating Effectiveness of Feedback in SQL-Tutor. International Workshop for Advanced Learning Technologies IWALT2000, December 4-6, 2000, Palmerston North, pp. 143-144.
  • Mayo, M., Mitrovic, A. Using a probabilistic student model to control problem difficulty. Proc. ITS'2000, G. Gauthier, C. Frasson and K. VanLehn (eds), Springer, pp. 524-533, 2000.

    Abstract: We present a new method for using the student model to solve decision problems in an ITS. While student models that can reasonably accurately predict student post-test performance have been developed, to be truly adaptive an ITS should use the student model to solve decision problems such as selecting feedback or next topic, and selective highlighting/hiding of information. We have developed one such approach to adaptive decision-making based on Bayesian probability theory. For each alternative, simple Bayesian networks make multiple predictions about student performance on atomic domain elements called constraints. These multiple predictions are then combined heuristically to give an overall measure of the value of the alternative. The approach is demonstrated in a problem selection module for SQL-Tutor, an ITS for teaching the SQL database language.


  • Mitrovic, A., Suraweera, P. Evaluating an Animated Pedagogical Agent. Proc. ITS'2000, G. Gauthier, C. Frasson and K. VanLehn (eds), Springer, pp. 73-82, 2000.

    Abstract: The paper presents SmartEgg, an animated pedagogical agent developed for SQLT-Web, an intelligent SQL tutor on the Web. It has been shown in previous studies that pedagogical agents have a significant motivational impact on students. Our hypothesis was that even a very simple and constrained agent, like SmartEgg, would enhance learning. We report on an evaluation study that confirmed our hypothesis.


  • Porting SQL-Tutor to the Web. Mitrovic, A., Hausler, K. Proc. ITS'2000 workshop on Adaptive and Intelligent Web-based Education Systems, pp. 37-44, 2000.
  • Martin, B., Mitrovic, A. Tailoring Feedback by Correcting Student Answers. Proc. ITS'2000, G. Gauthier, C. Frasson and K. VanLehn (eds), Springer, pp. 383-392, 2000.

    Abstract: Constraint-based models represent the domain by describing states into which a solution may fall, and testing that solutions in a state are consistent with the problem being solved. Constraints have a relevance condition (which defines the state) and a satisfaction condition (which tests the integrity of the solution.) In this paper we present a purely pattern-based representation for constraints, and describe a method for using it to generate correct solutions based on students' incorrect answers. This method will be used to tailor feedback, by presenting the student with correct examples that most closely match their attempts.


  • Martin, B., Mitrovic, A. Induction of Higher-Order Knowledge in Constraint-Based Models. ITS'2000 workshop on Applying Machine Learning to ITS Design/Construction, pp. 31-36, 2000.
  • Martin, B. Learning constraints by asking questions. ITS'2000 workshop on Applying Machine Learning to ITS Design/Construction, pp. 25-30, 2000.
  • Evaluation of a Constraint-Based Tutor for a Database Language

    Mitrovic, A. Ohlsson, S. Int. J. on Artificial Intelligence in Education, 10(3-4), 1999, pp. 238-256.
    Abstract: We propose a novel approach to intelligent tutoring in which feedback messages are associated with constraints on correct problem solution. The knowledge state of the student is represented by the constraints that he or she does and does not violate during problem solving. Constraint-based tutoring has been implemented in SQL-Tutor, an intelligent tutoring system for teaching the database query language SQL. Empirical evaluation shows that (a) students find the system easy to use, and (b) they do better on a subsequent classroom examination than peers without experience with the system. Furthermore, learning curves are smooth when plotted in terms of individual constraints, supporting the psychological appropriateness of the constraint construct.


  • Mayo, M., Mitrovic, A. Estimating Problem Value in an Intelligent Tutoring System using Bayesian Networks. Proc. AI'99, Sydney, Dec 1999, pp. 472-3.
  • Learning SQL with a computerized tutor

    Mitrovic, A. Proc. ACM SIGCSE'98, Atlanta, February 25th-March 1st, 1998, pp. 307-311.

    Abstract: SQL, the dominant database language, is a simple and highly structured language; yet, students have many difficulties learning it. This paper presents SQL-Tutor, an Intelligent Tutoring System designed as a guided discovery learning environment, which helps students in overcoming these difficulties. We present design issues and the current state in the implementation of the system, with special focus on individualization of instruction towards a particular student.


  • A Knowledge-Based Teaching System for SQL

    Mitrovic, A. Proc. ED-MEDIA/ED-TELECOM'98, Freiburg, June 20-25, 1998, pp. 1027-1032.

    Abstract: The paper presents SQL-Tutor, an intelligent teaching system for SQL programming. SQL-Tutor is designed as a guided discovery learning environment and supports problem solving, conceptual and meta-learning. The system uses Constraint-Based Modeling to form models of its students. We present design issues by focusing on the system's architecture. Student modeling and the generation of pedagogical actions are discussed in the light of tailoring instructions towards a particular student.


  • Experiences in Implementing Constraint-Based Modeling in SQl-Tutor

    Mitrovic, A. Proc. ITS'98, San Antonio, 17-19 August 1998, pp. 414-423.

    Abstract: The problem with most student modeling approaches is their insistence on complete and cognitively valid models of student's knowledge. Ohlsson [10] proposes Constraint-Based Modeling (CBM) as a way to overcome intractability of student modeling, by generating models that are precise enough to guide instruction, and are computationally tractable at the same time. The paper presents our experiences in building \tut{}, an ITS built upon CBM. CBM is extremely computationally efficient. State constraints, which form the basis of CBM, are very expressive; we have encountered no situations where constraints were unable to diagnose student answers. The time needed to acquire, implement and test a constraint is less than times reported for the acquisition of production rules. \tut{} will soon be used in laboratory sessions, and we expect that our flawless experiences with CBM will be repeated in real use.


  • SQL-Tutor: a preliminary report

    Mitrovic, A. Research Report, Computer Science Department, University of Canterbury, August 1997

    Abstract: Intelligent Tutoring Systems (ITS) are computer systems which provide students with learning environments adapted to their knowledge and learning capabilities. This paper presents SQL-Tutor, an ITS for SQL programming. SQL, the dominant database language, is a simple and highly structured language; yet, students have many difficulties learning it. SQL-Tutor is designed as a guided discovery learning environment which helps students in overcoming these difficulties. We present design issues and the current state in the implementation of the system, with special focus on individualization of instruction towards a particular student.


  • SINT - a Symbolic Integration Tutor

    Mitrovic, A. Proceedings of ITS'96 conference, Montreal, June 1996, Lecture Notes in Computer Science, C. Frasson, G. Gauthier, A. Lesgold (eds), Springer, pp.587-595.

    Abstract: We present an intelligent tutoring system in the area of symbolic integration. The system is capable of solving problems step-by-step along with the student. SINT monitors the student while solving problems, informs the student of errors and provides individualized help and advice when appropriate. The main focus of the research was on student modeling. The technique developed, referred to as INSTRUCT, builds on two well-known paradigms, reconstructive modeling and model tracing, at the same time avoiding their major pitfalls. The approach is not only incremental but truly interactive, since it involves the student in explicit dialogues about his/her goals. The student model is used to guide the generation of instructional actions, like generation of explanations and new problems.


  • INSTRUCT: Modeling Students by Asking Questions

    Mitrovic, A. User Modeling and User-Adapted Interaction, Vol. 6, No. 4, pp. 273-302, 1996.

    Abstract: The paper reports an approach to inducing models of procedural skills from observed student performance. The approach, referred to as INSTRUCT, builds on two well-known techniques, reconstructive modeling and model tracing, at the same time avoiding their major pitfalls. INSTRUCT does not require prior empirical knowledge of student errors and is also neutral with respect to pedagogy and reasoning strategies applied by the student. Pedagogical actions and the student model are generated on-line, which allows for dynamic adaptation of instruction, problem generation and immediate feedback on student's errors. Furthermore, the approach is not only incremental but truly interactive, since it involves students in explicit dialogues about their goals and problem-solving decisions. Student behaviour is used as a source of information for user modeling and to compensate for the unreliability of the student model. INSTRUCT uses both implicit information about the steps the student performed or the explanations he or she asked for, and explicit information gained from the student's answers to direct question about his or her goals and operations being performed. Domain knowledge and the user model are used to focus the search on the portion of the problem space the student is likely to traverse while solving the problem at hand. The approach presented is examined in the context of SINT, an ITS for the domain of symbolic integration.


  • Interactive Reconstructive Student Modeling: a Machine Learning Approach

    Mitrovic, A. Int. J. Human-Computer Interaction, Vol 7(4), 385-401, 1995.

    Abstract: Reconstructive bug modeling is a well-known approach to student modeling in intelligent tutoring systems, suitable for modeling procedural tasks. Domain knowledge is decomposed into the set of primitive operators and the set of conditions of their applicability. Reconstructive modeling is capable of describing errors that come from irregular application of correct operators. The main obstacle to successfulness of this approach is such decomposition of domain knowledge to primitive operators with very low level of abstraction, so that bugs could never occur within them. The other drawback of this modeling scheme is its efficiency, since it is usually done off--line, due to vast search spaces involved.

    This paper reports a novel approach to reconstructive modeling based on machine learning techniques for inducing procedures from traces. The approach overcomes the problems of reconstructive modeling by its interactive nature. It allows on--line model generation by using domain knowledge and knowledge about the student to focus the search on the portion of the problem space the student is likely to traverse while solving the problem. Furthermore, the approach is not only incremental but truly interactive, since it involves the student in explicit dialogs about his goals. In such a way, it is possible to determine whether the student knows the operator he is trying to apply. Pedagogical actions and the student model are generated interchangeably, thus allowing for dynamic adaptation of instruction, problem generation and immediate feedback on student's errors. The approach presented is examined in the context of the SINT system, an ITS for the domain of symbolic integration.


Disclaimer: The opinions expressed in this document are those of the author, not the University of Canterbury nor its Council.

Send mail to Tanja Mitrovic with questions or comments about this web site.
Copyright © 1995-2008 Intelligent Computer Tutoring Group
Last modified: August 7, 2008