An Examination of the Effectiveness of Social Tagging for Resource Discovery

Abstract

Social tagging allows users to assign keywords (tags) to resources facilitating their future access by the tag creator, and possibly by other users. In terms of its support for resource discovery, social tagging has both proponents and critics. The goal of this paper investigates if tags are an effective means for helping users locate useful resources. Adopting techniques from text categorization, we downloaded Web pages and their associated tags from del.icio.us, and trained Support Vector Machine classifiers to determine if the documents could be assigned to their associated tags. Results from the classifiers in terms of precision, recall and F1 score were mixed, suggesting that that not all tags could be used by public users for resource discovery. Detailed analyses of our results revealed characteristics of effective and ineffective tags for resource discovery. From these, implications for social tagging systems are discussed.