Finding Relevant e-Learning Materials

Abstract

Learners in e-Learning environments often have difficulty finding and retrieving relevant learning materials to support their learning goals because they lack sufficient domain knowledge to craft effective queries that convey what they wish to learn. In addition, the unfamiliar vocabulary often used by domain experts makes it difficult to map learners’ queries to relevant documents. Hence the need to develop a suitable method that would support finding and recommending relevant learning materials to learners. These challenges are addressed by exploiting a knowledge-rich method that automatically creates custom background knowledge in the form of a set of rich concepts related to the selected learning domain. A method is developed which allows the background knowledge to influence the refinement of queries during the recommendation of learning materials. The effectiveness of this approach is evaluated on a dataset of Machine Learning and Data Mining documents and it is shown to outperform benchmark methods. The results confirm that adopting a knowledge-rich representation within e-Learning recommendation improves the ability to find and recommend relevant e-Learning materials to learners.