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
Index Terms—Collaborative filtering, content based filtering, item-based recommendation, tag-based recommendation, knowledge management system.
Worasit Choochaiwattana is with the Search Engines and Intelligent Information Systems Research Laboratory, Faculty of Information Technology, Dhurakij Pundit University, Bangkok, Thailand (e-mail: firstname.lastname@example.org).
Cite: Worasit Choochaiwattana, "A Comparison between Item-Based and Tag-Based Recommendation on a Knowledge Management System: A Preliminary Investigation," International Journal of Information and Education Technology vol. 5, no. 10, pp. 754-757, 2015.