Social bookmarking systems and their emergent information structures, known as folksonomies, are increasingly important data sources for Semantic Web applications. A key question for harvesting semantics from these systems is how to extend and adapt traditional notions of similarity to folksonomies, and which measures are best suited for applications such as navigation support, semantic search, and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures derived from established information-theoretic, statistical, and practical measures. Our framework deals generally and symmetrically with users, tags, and resources. For evaluation purposes we focus on similarity among tags and resources, considering different ways to aggregate annotations across users. After comparing how tag similarity measures predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory. We also investigate the issue of scalability. We find that mutual information with distributional micro-aggregation across users yields the highest accuracy, but is not scalable; per-user projection with collaborative aggregation provides the best scalable approach via incremental computations. The results are consistent across resource and tag similarity.
W. Ebner, J. Leimeister, und H. Krcmar. Proceedings of the Hawai'i International Conference on System Sciences (HICSS), 37, Big Island, Hawaii, Hawaii International Conference on System Sciences, (Januar 2004)
A. Sunyaev, M. Reeber, J. Leimeister, und H. Krcmar. Proceedings of the Fifteenth Americas Conference on Information Systems (AMCIS), 15, San Francisco, USA, (2009)130 (14-09).
O. Bohl, S. Manouchehri, und U. Winand. Mobile Information Systems. Special Issue: Improving Quality of Service in Mobile Information Systems, Services and Networks3 (3-4):
135-152(2007)
S. Manouchehri, und U. Winand. Handbook of Research on Web 2.0, 3.0 and X.0: Technologies, Business and Social Applications, IGI Global, Hershey, USA, (2009)
F. Köbler, J. Leimeister, und A. Lugmayr. 14th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP06), Washington, DC, USA, (2006)EXT5.
H. v. Kortzfleisch, I. Mergel, S. Manouchehri, und M. Schaarschmidt. Web 2.0 Neue Perspektiven im E-Business, Web 2.0 Neue Perspektiven für Marketing und Medien, Springer Verlag, Berlin, Web 2.0 Neue Perspektiven für Marketing und Medien.(2007)
O. Bohl, und S. Manouchehri. Handbook of Research on Social Interaction Technologies and Collaboration Software: Concepts and Trends, Hershey, USA, (2009)