Improving CBR adaptation for recommendation of associated references in a knowledge-based learning assistant system

Abstract Case adaptation is a challenging phase of case-based reasoning (CBR) for recommendation of a matched case solution. Our proposed knowledge-based recommendation system analyzes the combination of visual and textual information in CBR medical system. In this paper a case-based reasoner uses medical expressions in a textual analysis to create word association profiles. Case-based Learning Assistant System (DePicT CLASS) finds significant references and learning materials by utilizing profile of words associations according to the problem description. This research proposes a new adaptation mechanism based on substitution, abstraction, and compositional method for collaborative recommendation in medical vocational educational training. The DePicT CLASS adaptation mechanism has a combination of value comparison based on requested word association profiles and manual adaptation based on user collaborative recommendation. In the adaptation process of the system, attract rate and adapt rate are defined and utilized for evaluating the adaptation results. Therefore, recommendation is a combination of references and learning materials with highest valued keyword association strength from the most similar cases.