The success and popularity of social network systems, such as del.icio.us, Facebook, MySpace, and YouTube, have generated many interesting and challenging problems to the research community. Among others, discovering social interests shared by groups of users is very important because it helps to connect people with common interests and encourages people to contribute and share more contents. The main challenge to solving this problem comes from the diffi- culty of detecting and representing the interest of the users. The existing approaches are all based on the online connections of users and so unable to identify the common interest of users who have no online connections. In this paper, we propose a novel social interest discovery approach based on user-generated tags. Our approach is motivated by the key observation that in a social network, human users tend to use descriptive tags to annotate the contents that they are interested in. Our analysis on a large amount of real-world traces reveals that in general, user-generated tags are consistent with the web content they are attached to, while more concise and closer to the understanding and judgments of human users about the content. Thus, patterns of frequent co-occurrences of user tags can be used to characterize and capture topics of user interests. We have developed an Internet Social Interest Discovery system, ISID, to discover the common user interests and cluster users and their saved URLs by different interest topics. Our evaluation shows that ISID can effectively cluster similar documents by interest topics and discover user communities with common interests no matter if they have any online connections.

@inproceedings{xin2008www, author = {Li, Xin and Guo, Lei and Zhao, Yihong E.}, title = {Tag-based Social Interest Discovery}, booktitle = {Proceedings of the 17th International World Wide Web Conference}, publisher = {ACM}, year = {2008}, pages = {675-684}, url = {http://www2008.org/papers/pdf/p675-liA.pdf}, keywords = {***, association, clustering, community, del.icio.us, detection, folksonomy, rules}, abstract = {The success and popularity of social network systems, such as del.icio.us, Facebook, MySpace, and YouTube, have generated many interesting and challenging problems to the research community. Among others, discovering social interests shared by groups of users is very important because it helps to connect people with common interests and encourages people to contribute and share more contents. The main challenge to solving this problem comes from the diffi- culty of detecting and representing the interest of the users. The existing approaches are all based on the online connections of users and so unable to identify the common interest of users who have no online connections. In this paper, we propose a novel social interest discovery approach based on user-generated tags. Our approach is motivated by the key observation that in a social network, human users tend to use descriptive tags to annotate the contents that they are interested in. Our analysis on a large amount of real-world traces reveals that in general, user-generated tags are consistent with the web content they are attached to, while more concise and closer to the understanding and judgments of human users about the content. Thus, patterns of frequent co-occurrences of user tags can be used to characterize and capture topics of user interests. We have developed an Internet Social Interest Discovery system, ISID, to discover the common user interests and cluster users and their saved URLs by different interest topics. Our evaluation shows that ISID can effectively cluster similar documents by interest topics and discover user communities with common interests no matter if they have any online connections.} }

%0 = inproceedings %A = Li, Xin and Guo, Lei and Zhao, Yihong E. %B = Proceedings of the 17th International World Wide Web Conference %D = 2008 %I = ACM %T = Tag-based Social Interest Discovery %U = http://www2008.org/papers/pdf/p675-liA.pdf

@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 (Proc. IFCS 2006 Conference)}, series = {Studies in Classification, Data Analysis, and Knowledge Organization}, publisher = {Springer}, address = {Berlin/Heidelberg}, year = {2006}, pages = {261-270}, note = {Ljubljana}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/schmitz2006asso_ifcs.pdf}, doi = {10.1007/3-540-34416-0_28}, isbn = {978-3-540-34415-5}, keywords = {2006, analysis, association, folksonomy, kdubiq, myown, network, rules, semantic, seminar2006, sosbuch, summerschool} }

%0 = inproceedings %A = Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd %B = Data Science and Classification (Proc. IFCS 2006 Conference) %C = Berlin/Heidelberg %D = 2006 %I = Springer %T = Mining Association Rules in Folksonomies %U = http://www.kde.cs.uni-kassel.de/hotho/pub/2006/schmitz2006asso_ifcs.pdf

@inproceedings{conf/sigmod/NgLHP98, author = {Ng, Raymond T. and Lakshmanan, Laks V. S. and Han, Jiawei and Pang, Alex}, title = {Exploratory Mining and Pruning Optimizations of Constrained Association Rules.}, booktitle = {SIGMOD Conference}, year = {1998}, pages = {13-24}, url = {http://dblp.uni-trier.de/db/conf/sigmod/sigmod98.html#NgLHP98}, keywords = {2006, lecture, rules, association, constraints, kdd, mining} }

%0 = inproceedings %A = Ng, Raymond T. and Lakshmanan, Laks V. S. and Han, Jiawei and Pang, Alex %B = SIGMOD Conference %D = 1998 %T = Exploratory Mining and Pruning Optimizations of Constrained Association Rules. %U = http://dblp.uni-trier.de/db/conf/sigmod/sigmod98.html#NgLHP98

@article{park1995ehb, author = {Park, J.S. and Chen, M.S. and Yu, P.S.}, title = {An effective hash-based algorithm for mining association rules}, journal = {Proceedings of the 1995 ACM SIGMOD international conference on Management of data}, publisher = {ACM Press New York, NY, USA}, year = {1995}, pages = {175-186}, keywords = {2006, table, lecture, rules, association, kdd, mining, hash} }

%0 = article %A = Park, J.S. and Chen, M.S. and Yu, P.S. %D = 1995 %I = ACM Press New York, NY, USA %T = An effective hash-based algorithm for mining association rules

@inproceedings{SrikantAgrawal95, author = {Srikant, R. and Agrawal, R.}, title = {Mining Generalized Association Rules}, booktitle = {Proceedings of the 21st International Conference on Very Large Databases}, year = {1995}, pages = {407--419}, keywords = {generalized, rules, association, mining} }

%0 = inproceedings %A = Srikant, R. and Agrawal, R. %B = Proceedings of the 21st International Conference on Very Large Databases %D = 1995 %T = Mining Generalized Association Rules

@inproceedings{agrawal93, author = {Agrawal, Rakesh and Imielinski, Tomasz and Swami, Arun}, title = {Mining association rules between sets of items in large databases}, booktitle = {SIGMOD '93: Proceedings of the 1993 ACM SIGMOD international conference on Management of data}, publisher = {ACM Press}, address = {New York, NY, USA}, year = {1993}, pages = {207--216}, keywords = {association, basic, mining, ml, rules} }

%0 = inproceedings %A = Agrawal, Rakesh and Imielinski, Tomasz and Swami, Arun %B = SIGMOD '93: Proceedings of the 1993 ACM SIGMOD international conference on Management of data %C = New York, NY, USA %D = 1993 %I = ACM Press %T = Mining association rules between sets of items in large databases