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

@article{cattuto2007, author = {Cattuto, C. and Schmitz, C. and Baldassarri, A. and Servedio, V. D. P. and Loreto, V. and Hotho, A. and Grahl, M. and Stumme, G.}, title = {Network Properties of Folksonomies}, journal = {AI Communications}, year = {2007}, volume = {20}, number = {4}, pages = {245 - 262}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2007/aicomm_2007_folksonomy_clustering.pdf}, keywords = {clustering, community, folksonomy} }

%0 = article %A = Cattuto, C. and Schmitz, C. and Baldassarri, A. and Servedio, V. D. P. and Loreto, V. and Hotho, A. and Grahl, M. and Stumme, G. %D = 2007 %T = Network Properties of Folksonomies %U = http://www.kde.cs.uni-kassel.de/hotho/pub/2007/aicomm_2007_folksonomy_clustering.pdf

The investigation of community structures in networks is an important issue
many domains and disciplines. This problem is relevant for social tasks
bjective analysis of relationships on the web), biological inquiries
unctional studies in metabolic, cellular or protein networks) or
chnological problems (optimization of large infrastructures). Several types
algorithm exist for revealing the community structure in networks, but a
neral and quantitative definition of community is still lacking, leading to
intrinsic difficulty in the interpretation of the results of the algorithms
thout any additional non-topological information. In this paper we face this
oblem by introducing two quantitative definitions of community and by showing
w they are implemented in practice in the existing algorithms. In this way
e algorithms for the identification of the community structure become fully
lf-contained. Furthermore, we propose a new local algorithm to detect
mmunities which outperforms the existing algorithms with respect to the
mputational cost, keeping the same level of reliability. The new algorithm is
sted on artificial and real-world graphs. In particular we show the
plication of the new algorithm to a network of scientific collaborations,
ich, for its size, can not be attacked with the usual methods. This new class
local algorithms could open the way to applications to large-scale
chnological and biological applications.

@misc{citeulike:341233, author = {Radicchi, Filippo and Castellano, Claudio and Cecconi, Federico and Loreto, Vittorio and Parisi, Domenico}, title = {Defining and identifying communities in networks}, year = {2004}, url = {http://arxiv.org/abs/cond-mat/0309488}, keywords = {clustering, folksonomy, toread, graph, community}, abstract = {The investigation of community structures in networks is an important issue in many domains and disciplines. This problem is relevant for social tasks (objective analysis of relationships on the web), biological inquiries (functional studies in metabolic, cellular or protein networks) or technological problems (optimization of large infrastructures). Several types of algorithm exist for revealing the community structure in networks, but a general and quantitative definition of community is still lacking, leading to an intrinsic difficulty in the interpretation of the results of the algorithms without any additional non-topological information. In this paper we face this problem by introducing two quantitative definitions of community and by showing how they are implemented in practice in the existing algorithms. In this way the algorithms for the identification of the community structure become fully self-contained. Furthermore, we propose a new local algorithm to detect communities which outperforms the existing algorithms with respect to the computational cost, keeping the same level of reliability. The new algorithm is tested on artificial and real-world graphs. In particular we show the application of the new algorithm to a network of scientific collaborations, which, for its size, can not be attacked with the usual methods. This new class of local algorithms could open the way to applications to large-scale technological and biological applications.} }

%0 = misc %A = Radicchi, Filippo and Castellano, Claudio and Cecconi, Federico and Loreto, Vittorio and Parisi, Domenico %B = } %C = %D = 2004 %I = %T = Defining and identifying communities in networks} %U = http://arxiv.org/abs/cond-mat/0309488