rules with 0.05 support, and 10 confidence on K2. Only associations rules with one element in premise and one element in conclusion are considered in the graph In the figure 3 we identified four major areas in the graph which we labeled with the topics delicious hacks, Javascript, Ajar, and CsS. The topics can be derived by applying the FolkRank(hotho et al.(2006))on some of the resources of interest, which also yields relevant users and other resources for the respective area, such that communities of interest can be identified 6 Conclusion n this paper, we have presented a formal model of folksonomies as a set of triples -or, equivalently, a tripartite hypergraph. In order to apply associ- ation rule mining to folksonomies, we have systematically explored possible projections of the folksonomy structure into the standard notion of"shopping baskets"used in rule mining For two selected projec e demonstrated the outcome of rule on a large-scale folksonomy dataset. The rules can be applied for different pur poses, such as recommending tags, users, or resources, populating the supertag relation of the folksonomy, and community detection Future work includes the tighter integration of the various techniques we used here, namely, association rule mining, FolkRank ranking, and graph clus- tering, to further contribute to the abovementioned applications References AGRAWAL, R, IMIELINSKI, T and SWAMI, A(1993): Mining association rules between sets of items in large databases. In: Proc. of SIGMOD 1993, pp. 207-216 ACM Press ConnOtea(2005):conNoteaMailingList.https://lists.sourceforge.net/lists/ istinfo/connotea-discuss GANTER, B and WILLE, R(1999): Formal Concept Analysis Mathematical foun dations. Springe HAMMOND, T, HANNAY, T, LUND, B and SCOTT, J (2005 ) Social Bookmark ing Tools(I): A General Review. D-Lib Magazine, 11 (4) HOTHO, A, JASCHKE, R, SCHMITZ, C and STUMME, G(2006): Information Retrieval in Folksonomies: Search and Ranking. In: submitted for publication at ESWC 2006 LEHMANN, F and WILLE, R(1995): A triadic approach to Formal Concept Anal ysis. In: G. Ellis, R. Levinson, W. Rich and J. F. Sowa(Eds ) Conceptual Structures: Applications, Implementation and Theory, vol 954 of Lecture Notes in Computer Science. Springer. ISBN 3-540-60161-9 HANNAY, T.(2005 ) Social Bookmarking Tools(II): A Case Study - Connotea D-Lib Magazine, 11(4) MATHES, A(2004): Folksonomies-Cooperative Classification and Communication hroughSharedMetadata.http://www.adammathes.com/academic/computer- mediated-communication/folksonomies. html MIKA, P.(2005: Ontologies Are Us: A Unified Model of Social Networks and Se mantics. In: Y. Gil, E. Motta, V. R. Benjamins and M. A. Musen(Eds ) ISWC 05, vol 3729 of LNCS, pp 522-536. Springer-Verlag, Berlin Heidelbergrules with 0.05 % support, and 10 % confidence on K2. Only associations rules with one element in premise and one element in conclusion are considered in the graph. In the figure 3 we identified four major areas in the graph which we labeled with the topics delicious hacks, Javascript, Ajax, and CSS. The topics can be derived by applying the FolkRank (Hotho et al. (2006)) on some of the resources of interest, which also yields relevant users and other resources for the respective area, such that communities of interest can be identified. 6 Conclusion In this paper, we have presented a formal model of folksonomies as a set of triples – or, equivalently, a tripartite hypergraph. In order to apply associ￾ation rule mining to folksonomies, we have systematically explored possible projections of the folksonomy structure into the standard notion of “shopping baskets” used in rule mining. For two selected projections, we demonstrated the outcome of rule mining on a large-scale folksonomy dataset. The rules can be applied for different pur￾poses, such as recommending tags, users, or resources, populating the supertag relation of the folksonomy, and community detection. Future work includes the tighter integration of the various techniques we used here, namely, association rule mining, FolkRank ranking, and graph clus￾tering, to further contribute to the abovementioned applications. References AGRAWAL, R., IMIELINSKI, T. and SWAMI, A. (1993): Mining association rules between sets of items in large databases. In: Proc. of SIGMOD 1993, pp. 207–216. ACM Press. CONNOTEA (2005): Connotea Mailing List. https://lists.sourceforge.net/lists/ listinfo/connotea-discuss. GANTER, B. and WILLE, R. (1999): Formal Concept Analysis : Mathematical foun￾dations. Springer. HAMMOND, T., HANNAY, T., LUND, B. and SCOTT, J. (2005): Social Bookmark￾ing Tools (I): A General Review. D-Lib Magazine, 11 (4). HOTHO, A., JASCHKE, R., SCHMITZ, C. and STUMME, G. (2006): Information ¨ Retrieval in Folksonomies: Search and Ranking. In: submitted for publication at ESWC 2006. LEHMANN, F. and WILLE, R. (1995): A triadic approach to Formal Concept Anal￾ysis. In: G. Ellis, R. Levinson, W. Rich and J. F. Sowa (Eds.), Conceptual Structures: Applications, Implementation and Theory, vol. 954 of Lecture Notes in Computer Science. Springer. ISBN 3-540-60161-9. HANNAY, T. (2005): Social Bookmarking Tools (II): A Case Study - Connotea. D-Lib Magazine, 11 (4). MATHES, A. (2004): Folksonomies – Cooperative Classification and Communication Through Shared Metadata. http://www.adammathes.com/academic/computer￾mediated-communication/folksonomies.html. MIKA, P. (2005): Ontologies Are Us: A Unified Model of Social Networks and Se￾mantics. In: Y. Gil, E. Motta, V. R. Benjamins and M. A. Musen (Eds.), ISWC 2005, vol. 3729 of LNCS, pp. 522–536. Springer-Verlag, Berlin Heidelberg. 8