AbstractMathematics is highly structured and also underpins most of science and
engineering. For this reason, it has proved a very suitable domain for Intelligent
Tutoring System (ITS) research, with the result that probably more tutoring systems have been constructed for the domain than any other. However, the literature reveals that there still exists no consensus on a credible approach or approaches for the design of such systems, despite numerous documented efforts. Current approaches to the construction of ITSs leave much to be desired. Consequently, existing ITSs in the domain suffer from a considerable number of shortcomings which render them 'unintelligent'.
The thesis examines some of the reasons why this is the case. Following a critical
review of existing ITSs in the domain, and some pilot studies, an alternative
approach to their construction is proposed (the 'iterative-style' approach); this
supports an iterative style, and also improves on at least some of the shortcomings of existing approaches.
The thesis also presents an ITS for fractions which has been developed using this
approach, and which has been evaluated in various ways. It has, demonstrably,
improved on many of the limitations of existing ITSs; furthermore, it has been
shown to be largely 'intelligent', at least more so than current tutors for the domain. Perhaps more significantly, the tutor has also been evaluated against real students with, so far, very encouraging results.
The thesis thus concludes that the novel iterative-style approach is a more credible approach to the construction of ITSs in mathematics than existing techniques.
|Date of Award||May 1989|
|Supervisor||Peter Coxhead (Supervisor)|
- intelligent tutoring systems
- artificial intelligence
- computer-assisted instruction
- bug theories