Domain model relations discovering in educational texts based on user created annotations

Domain model with its metadata is essential part of every adaptive educational system. At the same time it is often a bottleneck as quality metadata is essential requirement and their manual creation is difficult or even impossible in some extent. So any effort in automated acquisition of metadata is crucial for effective learning supported by an educational system. In this paper we propose a method of discovering relations in educational texts using annotations created by users (learners). As annotations we use links to external educational resources related to educational texts. We integrate external resources into the learning course and analyze their content. Based on the content analysis we construct a graph consisting of educational content, external resources and existing concepts in the domain model and use graph algorithms to derive new relations. Besides the benefit of discovered relations, our approach enriches educational content with additional information resources.