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 ?nd 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.

@inproceedings{markines2009evaluating, author = {Markines, Benjamin and Cattuto, Ciro and Menczer, Filippo and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, title = {Evaluating Similarity Measures for Emergent Semantics of Social Tagging}, booktitle = {18th International World Wide Web Conference}, year = {2009}, pages = {641--650}, url = {http://www2009.eprints.org/65/}, keywords = {2009, folksonomies, itegpub, l3s, measures, myown, similarity, sitc, sna, social_similarity, sota, tag, tagging, tagorapub, www2009}, abstract = {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 ?nd 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.} }

%0 = inproceedings %A = Markines, Benjamin and Cattuto, Ciro and Menczer, Filippo and Benz, Dominik and Hotho, Andreas and Stumme, Gerd %B = 18th International World Wide Web Conference %D = 2009 %T = Evaluating Similarity Measures for Emergent Semantics of Social Tagging %U = http://www2009.eprints.org/65/

@article{jaeschke08discovering, author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd}, title = {Discovering Shared Conceptualizations in Folksonomies}, journal = {Journal of Web Semantics}, year = {2008}, volume = {6}, number = {1}, pages = {38-53}, url = {http://dx.doi.org/10.1016/j.websem.2007.11.004}, keywords = {2008, FCA, OntologyHandbook, analysis, bibsonomy, concept, discovering, fca, folksonomies, formal, itegpub, l3s, myown, shared, triadic} }

%0 = article %A = Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd %D = 2008 %T = Discovering Shared Conceptualizations in Folksonomies %U = http://dx.doi.org/10.1016/j.websem.2007.11.004

@inproceedings{stumme05finite, author = {Stumme, Gerd}, title = {A Finite State Model for On-Line Analytical Processing in
Triadic Contexts}, editor = {Ganter, Bernhard and Godin, Robert}, booktitle = {Proc. 3rd Intl. Conf. on Formal Concept Analysis}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, address = {Heidelberg}, year = {2005}, volume = {3403}, pages = {315-328}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2005/stumme2005finite.pdf}, isbn = {3-540-24525-1}, keywords = {2005, fca, folksonomies, itegpub, l3s, myown, olap, triadic} }

%0 = inproceedings %A = Stumme, Gerd %B = Proc. 3rd Intl. Conf. on Formal Concept Analysis %C = Heidelberg %D = 2005 %I = Springer %T = A Finite State Model for On-Line Analytical Processing in
Triadic Contexts %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2005/stumme2005finite.pdf

Social bookmark tools are rapidly emerging on the Web. In such
stems users are setting up lightweight conceptual structures
lled folksonomies. These systems provide currently relatively few
ructure. We discuss in this paper, how association rule mining
n be adopted to analyze and structure folksonomies, and how the results can be used
r ontology learning and supporting emergent semantics. We
monstrate our approach on a large scale dataset stemming from an
line system.

@inproceedings{schmitz2006mining, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, title = {Mining Association Rules in Folksonomies}, editor = {Batagelj, V. and Bock, H.-H. and Ferligoj, A. and Žiberna, A.}, booktitle = {Data Science and Classification. Proceedings of the 10th IFCS Conf.}, series = {Studies in Classification, Data Analysis, and Knowledge Organization}, publisher = {Springer}, address = {Heidelberg}, year = {2006}, pages = {261--270}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006mining.pdf}, keywords = {2006, analysis, fca, folksonomies, folksonomy, l3s, myown, nepomuk, network, semantic}, abstract = {Social bookmark tools are rapidly emerging on the Web. In such
stems users are setting up lightweight conceptual structures
lled folksonomies. These systems provide currently relatively few
ructure. We discuss in this paper, how association rule mining
n be adopted to analyze and structure folksonomies, and how the results can be used
r ontology learning and supporting emergent semantics. We
monstrate our approach on a large scale dataset stemming from an
line system.} }

%0 = inproceedings %A = Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd %B = Data Science and Classification. Proceedings of the 10th IFCS Conf. %C = Heidelberg %D = 2006 %I = Springer %T = Mining Association Rules in Folksonomies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006mining.pdf

Query logs provide a valuable resource for preference information in search. A user clicking on a specific resource after submitting a query indicates that the resource has some relevance with respect to the query. To leverage the information ofquery logs, one can relate submitted queries from specific users to their clicked resources and build a tripartite graph ofusers, resources and queries. This graph resembles the folksonomy structure of social bookmarking systems, where users addtags to resources. In this article, we summarize our work on building folksonomies from query log files. The focus is on threecomparative studies of the system’s content, structure and semantics. Our results show that query logs incorporate typicalfolksonomy properties and that approaches to leverage the inherent semantics of folksonomies can be applied to query logsas well.

@article{benz2010query, author = {Benz, Dominik and Hotho, Andreas and Jäschke, Robert and Krause, Beate and Stumme, Gerd}, title = {Query Logs as Folksonomies}, journal = {Datenbank-Spektrum}, year = {2010}, volume = {10}, number = {1}, pages = {15--24}, url = {http://dx.doi.org/10.1007/s13222-010-0004-8}, keywords = {2010, folksonomies, folksonomy, info20, itegpub, l3s, log, logs, logsonomy, myown}, abstract = {Query logs provide a valuable resource for preference information in search. A user clicking on a specific resource after submitting a query indicates that the resource has some relevance with respect to the query. To leverage the information ofquery logs, one can relate submitted queries from specific users to their clicked resources and build a tripartite graph ofusers, resources and queries. This graph resembles the folksonomy structure of social bookmarking systems, where users addtags to resources. In this article, we summarize our work on building folksonomies from query log files. The focus is on threecomparative studies of the system’s content, structure and semantics. Our results show that query logs incorporate typicalfolksonomy properties and that approaches to leverage the inherent semantics of folksonomies can be applied to query logsas well. } }

%0 = article %A = Benz, Dominik and Hotho, Andreas and Jäschke, Robert and Krause, Beate and Stumme, Gerd %D = 2010 %T = Query Logs as Folksonomies %U = http://dx.doi.org/10.1007/s13222-010-0004-8

@article{cattuto2007networkb, author = {Cattuto, Ciro and Schmitz, Christoph and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio and Hotho, Andreas and Grahl, Miranda and Stumme, Gerd}, title = {Network Properties of Folksonomies}, editor = {Hoche, Susanne and Nürnberger, Andreas and Flach, Jürgen}, journal = {AI Communications Journal, Special Issue on ``Network Analysis in Natural Sciences and Engineering''}, publisher = {IOS Press}, year = {2007}, volume = {20}, number = {4}, pages = {245-262}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2007/cattuto2007network.pdf}, issn = {0921-7126}, keywords = {2007, semantics, emergent, folksonomy, tagorapub, folksonomies, l3s, network, itegpub, fca} }

%0 = article %A = Cattuto, Ciro and Schmitz, Christoph and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio and Hotho, Andreas and Grahl, Miranda and Stumme, Gerd %D = 2007 %I = IOS Press %T = Network Properties of Folksonomies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2007/cattuto2007network.pdf

Collaborative tagging systems allow users to assign keywords—so called “tags”—to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied.
this paper we evaluate and compare two recommendation algorithms on largescale real life datasets: an adaptation of user-based collaborative filtering and a graph-based recommender built on top of FolkRank. We show that both provide better results than non-personalized baseline methods. Especially the graph-based recommender outperforms existing methods considerably.

@inproceedings{jaeschke2007tag, author = {Jäschke, Robert and Marinho, Leandro Balby and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, title = {Tag Recommendations in Folksonomies}, editor = {Kok, Joost N. and Koronacki, Jacek and de Mántaras, Ramon López and Matwin, Stan and Mladenic, Dunja and Skowron, Andrzej}, booktitle = {Knowledge Discovery in Databases: PKDD 2007, 11th European Conference on Principles and Practice of Knowledge Discovery in Databases}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, address = {Berlin, Heidelberg}, year = {2007}, volume = {4702}, pages = {506-514}, url = {http://dx.doi.org/10.1007/978-3-540-74976-9_52}, isbn = {978-3-540-74975-2}, keywords = {2007, FolkRank, Folksonomies, Recommendations, folksonomies, itegpub, l3s, myown, nepomuk, ranking, recommendations, tagging}, abstract = {Collaborative tagging systems allow users to assign keywords—so called “tags”—to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied.
this paper we evaluate and compare two recommendation algorithms on largescale real life datasets: an adaptation of user-based collaborative filtering and a graph-based recommender built on top of FolkRank. We show that both provide better results than non-personalized baseline methods. Especially the graph-based recommender outperforms existing methods considerably.} }

%0 = inproceedings %A = Jäschke, Robert and Marinho, Leandro Balby and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd %B = Knowledge Discovery in Databases: PKDD 2007, 11th European Conference on Principles and Practice of Knowledge Discovery in Databases %C = Berlin, Heidelberg %D = 2007 %I = Springer %T = Tag Recommendations in Folksonomies %U = http://dx.doi.org/10.1007/978-3-540-74976-9_52

@article{jaeschke08discovering, author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd}, title = {Discovering Shared Conceptualizations in Folksonomies}, journal = {Journal of Web Semantics}, year = {2008}, volume = {6}, number = {1}, pages = {38-53}, url = {http://dx.doi.org/10.1016/j.websem.2007.11.004}, keywords = {2008, analysis, bibsonomy, concept, discovering, fca, folksonomies, formal, itegpub, l3s, myown, shared, triadic} }

%0 = article %A = Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd %D = 2008 %T = Discovering Shared Conceptualizations in Folksonomies %U = http://dx.doi.org/10.1016/j.websem.2007.11.004

@article{cattuto2007networkb, author = {Cattuto, Ciro and Schmitz, Christoph and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio and Hotho, Andreas and Grahl, Miranda and Stumme, Gerd}, title = {Network Properties of Folksonomies}, editor = {Hoche, Susanne and Nürnberger, Andreas and Flach, Jürgen}, journal = {AI Communications Journal, Special Issue on ``Network Analysis in Natural Sciences and Engineering''}, publisher = {IOS Press}, year = {2007}, volume = {20}, number = {4}, pages = {245-262}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2007/cattuto2007network.pdf}, issn = {0921-7126}, keywords = {2007, emergent, fca, folksonomies, folksonomy, itegpub, l3s, myown, network, semantics, tagorapub} }

%0 = article %A = Cattuto, Ciro and Schmitz, Christoph and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio and Hotho, Andreas and Grahl, Miranda and Stumme, Gerd %D = 2007 %I = IOS Press %T = Network Properties of Folksonomies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2007/cattuto2007network.pdf