TOWARDS KNOWLEDGE-BASED GENERATIVE LEARNING OBJECTS

Abstract

Today there are many efforts to shift the reuse dimension from component-based to generative reuse in the learning object (LO) domain. This requires more precise LO models and commonality-variability analysis. We propose a new knowledge-based model for representing LO instances. The model is based on factoring and aggre-gating knowledge units within a LO and is presented as a structure of interface and functionality. Interface serves for explicit describing knowledge communication to and from the LO. Functionality describes knowledge representation and managing. The model contributes to better compositionality, reusability and can be further generalized easily to support the personalized content delivery and automatic generation. Using the introduced model as a basis for generalization, we extended the known concept of generative LOs by linking domain commonality-variability analysis with meta-programming techniques for generating LO instances on demand from the generic LO specification.