International Journal of
Information and Education Technology

Abstract

Knowledge is one of the most important critical factor for the success of organizations. As huge collections of knowledge are stored in a knowledge management system, hence the development of an automated knowledge dissemination mechanism becomes a challenging task. To improve performance of such a system, a “knowledge recommendation service” should be embedded. This paper compared the effectiveness of two recommendation techniques namely, an item-based recommendation (a collaborative filtering technique) and a tag-based recommendation (a content-based filtering technique). In order to evaluate the performance of the two proposed recommendations, a group of knowledge management system users were ask to be participants in this research study. The percentage of accuracy in knowledge items recommendations was used as an evaluation metric. The result of the experiment revealed that the tag-based recommendation had an accuracy of 86.67%, which is higher than that of item-based recommendation. Thus, the tag-based recommendation showed a promising approach to the task of automated knowledge dissemination in a knowledge management system.