An ontology model for content recommendation in personalized learning environment

Abstract

Personalized Learning Environments (PLEs) are expected to enhance the learning experience by providing tailor-made services based on learner preferences. It is of utmost importance to provide a personalized system which can automatically adapt to learners' learning styles, knowledge level and intelligently recommend resources that would favor and improve the learning. The existing PLEs still exhibit cold-start problems and other issues related with mapping of learning style and learning object. To solve these issues and to improve the dynamicity of the PLEs, an appropriate learner/learning object model is very essential. In this paper, we introduce an ontology model which encapsulates both learner profile and learning object attributes, which can be used for the content recommendation in an e-learning platform. Learner profile is the representation of learner data which includes both static and dynamic characteristics of the learner. The static data is gathered directly from the learner using forms and questionnaires and dynamic data is collected by tracking the behavior of learners, while interacting through a learning management system. The proposed ontology also holds space for learning topics and their corresponding Learning Object (LO) characteristics. The elements which come under the educational category of IEEE LOM standard, is considered for tagging the selected learning objects in the ontology. The JENA API of Java programming language is used for developing the ontology. The data is described using Resource Description Framework (RDF) tools. We have developed an ontology model consisting of an adaptive learner profile and standard LO characteristics which can be used in content recommender systems of e-learning environment.