Case-Based Reasoning Model for Personalized Learning Path Recommendation in Example-Based Learning Activities
In a traditional teaching models students are passive learners and usually share a common learning path that is in most cases predefined and fixed. In this paper we describe the case-based model for personalized learning path recommendation in example-based learning activities. According to the proposed model, the primary source of the knowledge for recommendation is represented in the form of cases that represent previously experienced learning paths. A recommended learning path comprises appropriate learning examples and learning resources for a student to go through in order to achieve desired learning outcomes. To validate the effectiveness of the proposed model, we conducted an experimentation to evaluate the impact of the model to student learning progress.