Exploiting Additional Context for Graph-Based Tag Recommendations in Folksonomy Systems

Folksonomy systems enable users to participate in the Web content creation process by annotating (tagging) resources with freely chosen keywords. Still, it is an open issue how to exploit this user-created content, and how to process and use these emergent semantics effectively. We investigate how the context of Web resources can be utilized to improve recommended strategies in social tagging systems. We focus on the GroupMe! system, which enables users to create groups in order to bundle Web resources. GroupMe! groups form valuable context information for the resources contained in such groups. In this paper we exploit graph-based tag recommendation strategies, evaluate them in the GroupMe! dataset, and benchmark our results against other approaches. In our evaluations we show that graph-based strategies outperform other approaches, and show the immanent benefit of graph-based recommendation strategies which exploit the group context for recommending tags to untagged resources.