Abstract
It is difficult to generalize experiences of system development as methodologies for building meta-learning support systems. Thus, the importance of a model-based system development approach has been recognized. Such an approach contributes to systematic refinement of learning systems according to the model and moreover, knowledge can be accumulated on meta-learning system development based on it. In this paper, we adopt a model-oriented approach and undertake the following: (i) we adopt Kayashima's computational model as a basis to build a meta-learning process model and we extend it for meta-learning activities; (ii) we conceptualize five concepts that clarify the means to remove or eliminate the factors of difficulty; then (iii) we clarify design rationales of support functions embedded into our system to facilitate meta-learning processes based on the meta-learning process model.
