@inproceedings{grahl07conceptualKdml, author = {Grahl, Miranda and Hotho, Andreas and Stumme, Gerd}, booktitle = {Workshop Proceedings of Lernen -- Wissensentdeckung -- Adaptivität (LWA 2007)}, editor = {Hinneburg, Alexander}, interhash = {9c3bb05456bf11bcd88a1135de51f7d9}, intrahash = {6d5188d66564fe4ed7386e28868504de}, isbn = {978-3-86010-907-6}, month = sep, pages = {50-54}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, title = {Conceptual Clustering of Social Bookmark Sites}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2007/kdml_recommender_final.pdf}, vgwort = {14}, year = 2007 } @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.}, interhash = {fc5f2df61d28bc99b7e15029da125588}, intrahash = {d87e198a6d564ae8a8fe151e0a96fa0f}, journal = {AI Communications}, number = 4, pages = {245 - 262}, title = {Network Properties of Folksonomies}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2007/aicomm_2007_folksonomy_clustering.pdf}, vgwort = {67}, volume = 20, year = 2007 } @inproceedings{grahl07conceptualKdml, author = {Grahl, Miranda and Hotho, Andreas and Stumme, Gerd}, booktitle = {Workshop Proceedings of Lernen -- Wissensentdeckung -- Adaptivität (LWA 2007)}, editor = {Hinneburg, Alexander}, interhash = {9c3bb05456bf11bcd88a1135de51f7d9}, intrahash = {6d5188d66564fe4ed7386e28868504de}, isbn = {978-3-86010-907-6}, month = sep, pages = {50-54}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, title = {Conceptual Clustering of Social Bookmark Sites}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2007/kdml_recommender_final.pdf}, vgwort = {14}, year = 2007 } @inproceedings{shepitsen2008personalized, abstract = {Collaborative tagging applications allow Internet users to annotate resources with personalized tags. The complex network created by many annotations, often called a folksonomy, permits users the freedom to explore tags, resources or even other user's profiles unbound from a rigid predefined conceptual hierarchy. However, the freedom afforded users comes at a cost: an uncontrolled vocabulary can result in tag redundancy and ambiguity hindering navigation. Data mining techniques, such as clustering, provide a means to remedy these problems by identifying trends and reducing noise. Tag clusters can also be used as the basis for effective personalized recommendation assisting users in navigation. We present a personalization algorithm for recommendation in folksonomies which relies on hierarchical tag clusters. Our basic recommendation framework is independent of the clustering method, but we use a context-dependent variant of hierarchical agglomerative clustering which takes into account the user's current navigation context in cluster selection. We present extensive experimental results on two real world dataset. While the personalization algorithm is successful in both cases, our results suggest that folksonomies encompassing only one topic domain, rather than many topics, present an easier target for recommendation, perhaps because they are more focused and often less sparse. Furthermore, context dependent cluster selection, an integral step in our personalization algorithm, demonstrates more utility for recommendation in multi-topic folksonomies than in single-topic folksonomies. This observation suggests that topic selection is an important strategy for recommendation in multi-topic folksonomies.}, address = {New York, NY, USA}, author = {Shepitsen, Andriy and Gemmell, Jonathan and Mobasher, Bamshad and Burke, Robin}, booktitle = {RecSys '08: Proceedings of the 2008 ACM conference on Recommender systems}, doi = {10.1145/1454008.1454048}, interhash = {c9028129dd7cd8314673bd64cbb6198e}, intrahash = {a7552f8d8d5db4f867ae6e94e1a4442f}, isbn = {978-1-60558-093-7}, location = {Lausanne, Switzerland}, pages = {259--266}, publisher = {ACM}, title = {Personalized recommendation in social tagging systems using hierarchical clustering}, url = {http://portal.acm.org/citation.cfm?id=1454008.1454048}, year = 2008 } @article{1751-8121-41-22-224016, abstract = {We analyze CiteULike, an online collaborative tagging system where users bookmark and annotate scientific papers. Such a system can be naturally represented as a tri-partite graph whose nodes represent papers, users and tags connected by individual tag assignments. The semantics of tags is studied here, in order to uncover the hidden relationships between tags. We find that the clustering coefficient can be used to analyze the semantical patterns among tags.}, author = {Capocci, Andrea and Caldarelli, Guido}, interhash = {14c8ecbc38dcdae876c3f4401006e3bb}, intrahash = {2a219a2664c566b405420f720583643a}, journal = {Journal of Physics A: Mathematical and Theoretical}, number = 22, pages = {224016 (7pp)}, title = {Folksonomies and clustering in the collaborative system CiteULike}, url = {http://stacks.iop.org/1751-8121/41/224016}, volume = 41, year = 2008 } @inproceedings{xin2008www, 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.}, author = {Li, Xin and Guo, Lei and Zhao, Yihong E.}, booktitle = {Proceedings of the 17th International World Wide Web Conference}, interhash = {d7e6a5b8d215682b2a75add69c01de29}, intrahash = {42b4c94cff05ccef031235d661a7a77a}, pages = {675-684}, publisher = {ACM}, title = {Tag-based Social Interest Discovery}, url = {http://www2008.org/papers/pdf/p675-liA.pdf}, year = 2008 } @inproceedings{grahl2007clustering, abstract = {Currently, social bookmarking systems provide intuitive support for browsing locally their content. A global view is usually presented by the tag cloud of the system, but it does not allow a conceptual drill-down, e. g., along a conceptual hierarchy. In this paper, we present a clustering approach for computing such a conceptual hierarchy for a given folksonomy. The hierarchy is complemented with ranked lists of users and resources most related to each cluster. The rankings are computed using our FolkRank algorithm. We have evaluated our approach on large scale data from the del.icio.us bookmarking system.}, address = {Graz, Austria}, author = {Grahl, Miranda and Hotho, Andreas and Stumme, Gerd}, booktitle = {7th International Conference on Knowledge Management (I-KNOW '07)}, interhash = {5cf58d2fdd3c17f0b0c54ce098ff5b60}, intrahash = {334d3ab11400c4a3ea3ed5b1e95c1855}, issn = {0948-695x}, month = SEP, pages = {356-364}, publisher = {Know-Center}, title = {Conceptual Clustering of Social Bookmarking Sites}, vgwort = {14}, year = 2007 } @inproceedings{grahl07conceptualKdml, author = {Grahl, Miranda and Hotho, Andreas and Stumme, Gerd}, booktitle = {Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007)}, editor = {Hinneburg, Alexander}, interhash = {9c3bb05456bf11bcd88a1135de51f7d9}, intrahash = {6d5188d66564fe4ed7386e28868504de}, isbn = {978-3-86010-907-6}, month = sep, pages = {50-54}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, title = {Conceptual Clustering of Social Bookmark Sites}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2007/kdml_recommender_final.pdf}, vgwort = {14}, year = 2007 } @misc{golder05structure, author = {Golder, Scott and Huberman, Bernardo A.}, citeulike-article-id = {305755}, eprint = {cs.DL/0508082}, interhash = {2d312240f16eba52c5d73332bc868b95}, intrahash = {f852d7a909fa3edceb04abb7d2a20f71}, month = Aug, priority = {2}, title = {The Structure of Collaborative Tagging Systems}, url = {http://arxiv.org/abs/cs.DL/0508082}, year = 2005 } @inproceedings{schmitz06, author = {Schmitz, Patrick}, booktitle = {Collaborative Web Tagging Workshop at WWW2006, Edinburgh, Scotland}, interhash = {1335f4ef87f951e6edf4fd94f885d3a2}, intrahash = {77143fd854a06583430afae1371fad71}, month = May, title = {Inducing Ontology from Flickr Tags.}, url = {http://www.ibiblio.org/www_tagging/2006/22.pdf}, year = 2006 } @techreport{citeulike:739394, abstract = {Collaborative tagging systems---systems where many casual users annotate objects with free-form strings (tags) of their choosing---have recently emerged as a powerful way to label and organize large collections of data. During our recent investigation into these types of systems, we discovered a simple but remarkably effective algorithm for converting a large corpus of tags annotating objects in a tagging system into a navigable hierarchical taxonomy of tags. We first discuss the algorithm and then present a preliminary model to explain why it is so effective in these types of systems.}, author = {Heymann, Paul and Garcia-Molina, Hector}, citeulike-article-id = {739394}, institution = {Computer Science Department}, interhash = {d77846b40aadb0e25233cabf905bb93e}, intrahash = {3b4ce6fd7fa6dbf1c39fd261fa39fcd6}, month = {April}, number = {2006-10}, priority = {3}, school = {Standford University}, title = {Collaborative Creation of Communal Hierarchical Taxonomies in Social Tagging Systems}, url = {http://dbpubs.stanford.edu:8090/pub/2006-10}, year = 2006 } @inproceedings{Mika2005, author = {Mika, Peter}, bibsource = {DBLP, http://dblp.uni-trier.de}, booktitle = {International Semantic Web Conference}, doi = {10.1007/11574620_38}, ee = {http://dx.doi.org/10.1007/11574620_38}, interhash = {5ea12110b5bb0e3a8ad09aeb16a70cdb}, intrahash = {6929599cc8fbdc408282907eeec37204}, owner = {mlux}, pages = {522-536}, publisher = {Springer}, series = {LNCS}, timestamp = {2006.01.19}, title = {Ontologies Are Us: A Unified Model of Social Networks and Semantics}, url = {http://www.cs.vu.nl/~pmika/research/papers/ISWC-folksonomy.pdf}, year = 2005 } @misc{citeulike:341233, 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.}, author = {Radicchi, Filippo and Castellano, Claudio and Cecconi, Federico and Loreto, Vittorio and Parisi, Domenico}, citeulike-article-id = {341233}, comment = {"In general algorithms define communities operationally as what the they finds. A dendrogram, i. e. a community structure, is always produced by the algorithms down to the level of single nodes, independently from the type of graph analyzed. This is due to the lack of explicit prescriptions to discriminate between networks that are actually endowed with a community structure and those that are not. As a consequence, in practical applications one needs additional, non topological, information on the nature of the network to understand which of the branches of the tree have a real significance. Without such information it is not clear at all whether the identification of a community is reliable or not." --- Domain: scientific collaborations Task: calculate a dendrogram (the community graph) Method: effucuebt GN (Girvan \& Newman( algorithm based on edge betweenness. Their algorithm allows to be fine-tuned beween acting local or global. To be more efficient they replace the "edge betweenness" by "edge clustering coefficient" which is based on the number of triangles the edge is contained in VS the degree of the incident nodes. Motto: "Algorithm must include the quantitative community definition"}, eprint = {cond-mat/0309488}, interhash = {6ec9b00862909de405c08db1c9b43d63}, intrahash = {8634d935e0bf4d74a870d5c805612665}, month = Feb, priority = {0}, title = {Defining and identifying communities in networks}, url = {http://arxiv.org/abs/cond-mat/0309488}, year = 2004 } @misc{citeulike:155, abstract = {Inspired by empirical studies of networked systems such as the Internet, social networks, and biological networks, researchers have in recent years developed a variety of techniques and models to help us understand or predict the behavior of these systems. Here we review developments in this field, including such concepts as the small-world effect, degree distributions, clustering, network correlations, random graph models, models of network growth and preferential attachment, and dynamical processes taking place on networks.}, author = {Newman, M. E. J.}, citeulike-article-id = {155}, eprint = {cond-mat/0303516}, interhash = {7bedd01cb4c06af9f5200b0fb3faa571}, intrahash = {d53568209eef08fb0a8734cf34c59a71}, keywords = {affinity algorithm arch clustering complex-systems folksonomy growth information_retrieval math network network_theory readinggroup scale-free-networks small_world socialnetwork systems thesis web web-graph}, month = {March}, priority = {5}, title = {The structure and function of complex networks}, url = {http://arxiv.org/abs/cond-mat/0303516}, year = 2003 }