Summary: | 博士 === 國立成功大學 === 工程科學系碩博士班 === 95 === With vigorous development of Internet, especially the web page interaction technology, distant e-learning has become more and more realistic and popular. SCORM LOM, i.e. the Learning Object Metadata, enables the indexing and searching of learning objects in a learning object repository by extended sharing and searching features. However, LOM has a deficiency in semantic-awareness capability. Most LOM-based learning object retrieval mechanisms just provide keyword-based search. This thesis proposes an ontology-based framework for establishing personalized learning objects retrieval and recommendation. The personalization functionality is provided by the probabilistic semantic inferring of query terms, LOM-based user preference, and collaborative feedback. An ontology query expansion algorithm and an integrated learning objects ranking algorithm are proposed. Focused on digital learning material and contrasted to other traditional keyword-based search technologies, the proposed approach has shown significant improvement in retrieval precision, recall rate, and ranking performance.
|