TANGRAM for Personalized Learning Using the Semantic Web Technologies

Motivated with the goal to provide dynamic as-sembly and personalization of learning content parts, we propose an ontology-based solution implemented as an inte-grated learning environment called TANGRAM. TANGRAM relies on two ontologies for representing learn-ing object (LO) content structure and LO content type (i.e. pedagogical role). LO content described by those two on-tologies is further annotated with concepts of a domain on-tology, while a learning paths ontology is used to specify pedagogical relations (e.g. prerequisites) among domain concepts. A user model ontology is defined to represent rele-vant information about TANGRAM’s users. The paper pre-sents the employed ontologies, in the context of user model-ing and personalization. Furthermore, it describes the algo-rithm we defined to dynamically assemble content units into learning content personalized to the user’s domain knowl-edge, preferences, and learning styles. We also discuss our experiences with dynamic content generation and summa-rize results of the conducted evaluation study. Although TAGRAM is a general-purpose learning environment, in this paper, we analyze it in the domain of intelligent infor-mation systems. Index Terms—ontologies, personalized learning, semantic annotation, dynamic content assembly I.