Revising deductive knowledge and stereotypical knowledge in a student model

Abstract

A user/student model must be revised when new information about the user/student is obtained. But a sophisticated user/student model is a complex structure that contains different types of knowledge. Different techniques may be needed for revising different types of knowledge. This paper presents a student model maintenance system (SMMS) which deals with revision of two important types of knowledge in student models: deductive knowledge and stereotypical knowledge. In the SMMS, deductive knowledge is represented by justified beliefs. Its revision is accomplished by a combination of techniques involving reason maintenance and formal diagnosis. Stereotypical knowledge is represented in the Default Package Network (DPN). The DPN is a knowledge partitioning hierarchy in which each node contains concepts in a sub-domain. Revision of stereotypical knowledge is realized by propagating new information through the DPN to change default packages (stereotypes) of the nodes in the DPN. A revision of deductive knowledge may trigger a revision of stereotypical knowledge, which results in a desirable student model in which the two types of knowledge exist harmoniously.

Neural Network Based Stereotyping for User Profiles

“…¼ Reducing system overhead: it is widely recognised that the implementation and maintenance of neural networks is simpler than that of rule-based systems [8,9]. Furthermore, rule-based systems often involve either complicated conflict resolutions in default reasoning, or the belief value revision in evidential reasoning [6]. In contrast, the consistency can be easily maintained in neural network systems due to their ability to handle inconsistent or incomplete information.…”

“…Also, the neural network models can handle partial or erroneous cues without any ill-effect [15]. As discussed in Section 4.1, the conflict assumptions in input do not yield conflicting output, which is crucial for default reasoning [6]. ¼ Individualisation: as discussed in Section 2, the modelling process is not confined by predefined stereotypes (i.e.…”

“…Therefore, it is possible that the effort of maintaining consistency may bring in further conflicts in the subsequent interaction. Thus, model construction may fall into the dilemma where a non-monotonic process of reconciling conflicts is frequently involved, and eventually, no decision can be made after a period of interaction [6].…”

Generic User Modeling Systems

“…They were therefore expected to provide as many services as possible.`Concessions' in this regard were only made for shell systems in student-adaptive tutoring systems (Huang et al, 1991;Kono et al, 1994;Paiva and Self, 1995;Machado et al, 1999), which were expected to be usable for teaching different subject matters, but not for additional application domains besides educational ones.…”

Editorial

“…A comprehensive list would at least include GUMS (Finin, 1989), UMT (Brajnik and Tasso, 1994) and PROTUM (Vergara, 1994). If one also considers user modeling tool systems that provide a more limited user modeling functionality, then at least (Huang et al, 1991) and (Y. Kono and Mizoguchi, 1994) must be mentioned as well.…”