Combining Content-based and Collaborative Filters in Learning Object Selection
Article Sidebar
Keywords:
Collaborative filtering recommendation Content-based recommendation learning object learner model
Main Article Content
Abstract
The explosive growth of online digital learning resources that commonly referred to as “learning objects” in elearning community, demands effective recommendation solutions. We explore the hybrid techniques, which are by combining the content-based with the conditions of the learning object attributes and collaborative filtering with the condition of a learner similarity, to recommend the most suitable learning object to learners. The preferred content-based algorithm and nearest neighbor-based algorithm has been developed, combining with ranking method to strengthen predictive results. A learning object raking example is discussed to demonstrate the method implementation by using setting experiment. This result shows that the combining method can reduce the error rate of learner dissatisfaction.
Article Details
Section
ACTIS Article
It is the policy of ACTISNU to own the copyright to the published contributions on behalf of the interests of ACTISNU, its authors, and their employers, and to facilitate the appropriate reuse of this material by others. To comply with the Copyright Law, authors are required to sign an ACTISNU copyright transfer form before publication. This form, a copy of which appears in this journal (or website), returns to authors and their employers full rights to reuse their material for their own purposes.