User modelling in help systems
The User Modelling component of a shell for building Intelligent Help Systems (IHS) is described. An IHS helps users of interactive computer programs in accomplishing their tasks and within that context understanding of the specific application. Like other Intelligent Tutoring Systems, IHSs need to model the knowledge of the users concerning the target domain, i.c. a specific application. This User Model in EUROHELP as a data structure is nothing special: an overlay of the Domain Representation, augmented with a bug library. The focus of the paper is on the maintenance of the model by the User Modeller, which performs three functions: (1) Modelling learning, (2) modelling forgetting, and (3) checking the User Model. The first two functions are described, based on cognitive theories of human learning and memory. The last function is necessary because of the uncertain and yet experimental results of the first two models.
A prototype User Modeller exists and will be tested and tuned against empirical data of human learners of the Unix text editor Vi.
KeywordsLong Term Memory Information Processing System User Model Target Domain Knowledge State
Unable to display preview. Download preview PDF.
- 1.Anderson, J.R. (1983). The Architecture of Cognition. Harvard University Press, Cambridge.Google Scholar
- 2.Bower, G.H. & Hilgard, E.R. (1948; fifth ed. 1981). Theories of Learning.Google Scholar
- 3.Breuker, J.A., (1988). Coaching in Help Systems. In: J. Self (ed). Artificial Intelligence and Human Learning. Intelligent Computer-Aided Instruction. London: Chapman & Hall.Google Scholar
- 4.Breuker, J.A., Winkels, R.G.F. & Sandberg, J.A.C. (1987). A Shell for Intelligent Help Systems. Proceedings of the 10th International Joint Conference on Artificial Intelligence, 1, pp. 167–173.Google Scholar
- 5.Breuker, J.A., Duursma, C., Winkels, R.G.F. & Smith, M. (1989). Knowledge Representation in Eurohelp: Modelling operation and understanding of computer applications for Help Systems. Proceedings of the ESPRIT Conference 1989.Google Scholar
- 6.Clancey, W.J. (1986). Qualitative Student Models. Annual Reviews Computer Science, pp 381–450.Google Scholar
- 7.Greef, P. de & Breuker, J.A. (1985). User Modelling for Help Systems. Deliverable 12.2 of the ESPRIT Project P280, ‘EUROHELP'. University of Amsterdam.Google Scholar
- 8.Hartley, R. & Smith, M.J. (1988). Experiences in explanation giving in the EUROHELP Project. In: J. Self (ed). Artificial Intelligence and Human Learning. Intelligent Computer-Aided Instruction. London: Chapman & Hall.Google Scholar
- 9.Kass, R. (1987). The Role of User Modelling in Intelligent Tutoring Systems. Technical report MS-CIS-86-58, Dept. of Computer and Information Science, University of Pennsylvania.Google Scholar
- 10.Mulder, H. (1989). User Modelling in Eurohelp. Master thesis, University of Amsterdam.Google Scholar
- 11.Ross, P., Jones, J. & Millington, M. (1986). User Modelling in Intelligent Teaching and Tutoring. In: R. Lewis & E.D. Tag (eds). Trends in Computer Aided Education. Oxford: Blackwell.Google Scholar
- 12.Sandberg, J.A.C., Breuker, J.A. & Winkels, R.G.F. (1988). Research on HELP-systems: Empirical study and model construction. In: Kodratoff, Y.: Proceedings of the European Conference on Artificial Intelligence, Pitman Publishing, London, pp. 106–111.Google Scholar
- 13.Self, J. (1987). User Modelling in Open Learning Systems. Tutoring and Monitoring Facilities for European Open Learning.Google Scholar
- 14.Stehouwer, M. & Berkum, J. van (1989). Functional Specification of the Diagnoser. Report COE/EUROHELP/031. Courseware Europe BV.Google Scholar
- 15.Wickelgren, W.A. (1977). Learning and Memory. Academic Press, London.Google Scholar
- 16.Winkels, R.G.F. (1987). PSP — A Prototype Strategy Planner for IHSs. Deliverable 2.2.4 of the ESPRIT Project 280, ‘EUROHELP'. University of Amsterdam.Google Scholar
- 17.Winkels, R.G.F., Breuker, J.A. & Sandberg, J.A.C. (1988). Didactic Discourse in Intelligent Help Systems. Proceedings of the International Conference on Intelligent Tutoring Systems, Montréal, pp. 279–285.Google Scholar