Evaluating similarity measures for emergent semantics of social tagging Export

@inproceedings{markines07, abstract = {Social bookmarking systems are becoming increasingly important data sources for bootstrapping and maintaining Semantic Web applications. Their emergent information structures have become known as folksonomies. 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 community detection, navigation support, semantic search, user profiling and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures, which are derived from several 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 between tags and between resources and consider different methods to aggregate annotations across users. After comparing the ability of several tag similarity measures to predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory Project. 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.}, address = {New York, NY, USA}, author = {Markines, Benjamin and Cattuto, Ciro and Menczer, Filippo and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {WWW '09: Proceedings of the 18th international conference on World wide web}, citeulike-article-id = {4410217}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1526709.1526796}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1526709.1526796}, doi = {10.1145/1526709.1526796}, isbn = {978-1-60558-487-4}, keywords = {grounding, semantics, similarity, tagging}, location = {Madrid, Spain}, pages = {641--650}, posted-at = {2009-07-04 16:55:57}, priority = {3}, publisher = {ACM}, title = {Evaluating similarity measures for emergent semantics of social tagging}, url = {http://dx.doi.org/10.1145/1526709.1526796}, year = {2009} }

TY - CONF ID - markines07 L3 - citeulike-article-id:4410217 N2 - Social bookmarking systems are becoming increasingly important data sources for bootstrapping and maintaining Semantic Web applications. Their emergent information structures have become known as folksonomies. 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 community detection, navigation support, semantic search, user profiling and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures, which are derived from several 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 between tags and between resources and consider different methods to aggregate annotations across users. After comparing the ability of several tag similarity measures to predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory Project. 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. CY - Madrid, Spain SN - 978-1-60558-487-4 AD - New York, NY, USA EP - 650 TI - Evaluating similarity measures for emergent semantics of social tagging PB - ACM T2 - WWW '09: Proceedings of the 18th international conference on World wide web SP - 641 KW - grounding KW - semantics KW - similarity KW - tagging AU - Markines, Benjamin AU - Cattuto, Ciro AU - Menczer, Filippo AU - Benz, Dominik AU - Hotho, Andreas AU - Stumme, Gerd PY - 2009/// UR - http://dx.doi.org/10.1145/1526709.1526796 ER -