Innovative Modeling Techniques for Intelligent Tutoring Systems
Vladan Devedžić, Danijela Radovic, Ljubomir Jerinić · Studies in fuzziness and soft computing · 2000
This chapter describes three modeling techniques that have recently started to attract the attention of researchers and developers in the domain of intelligent tutoring systems (ITSs). These techniques are: hierarchical modeling, interoperable and reusable software components , and ontologies . All three of them have been used in developing a model of ITSs called GET-BITS (GEneric Tools for Building ITSs). The GET-BITS model has been used throughout the chapter in order to illustrate the techniques. The major goal of the chapter is to show how these three techniques can be used to make the internal organization of ITSs more natural, more flexible, and more robust, to enhance their design, and to improve their performance. Important modules of any intelligent tutoring system, like domain knowledge, pedagogical knowledge, student model, and explanation strategies, are discussed extensively in the context of the three modeling techniques and the GET-BITS model. Experience with using GET-BITS as the basis for building practical applications shows how the processes of computer-based tutoring and learning based on the GET-BITS model are much closer to human-based instruction. From the design perspective, major advantages of using hierarchical modeling, software components, and ontologies in developing practical ITSs include enhanced modularity, easy extensions, and important steps towards knowledge sharing and reuse. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.