@incollection{ADHMS:12, address = {Heidelberg, Germany}, alteditor = {Editor}, author = {Atzmueller, Martin and Doerfel, Stephan and Hotho, Andreas and Mitzlaff, Folke and Stumme, Gerd}, booktitle = {{Modeling and Mining Ubiquitous Social Media}}, interhash = {4f1f4b515b01cc448a91b3e368deabad}, intrahash = {d81d6f6ccdf3ff6572898d39c90e6354}, publisher = {Springer Verlag}, series = {LNAI}, title = {Face-to-Face Contacts at a Conference: Dynamics of Communities and Roles}, url = {http://www.kde.cs.uni-kassel.de/atzmueller/paper/atzmueller-face-to-face-contacts-dynamics-lnai-2012.pdf}, volume = 7472, year = 2012 } @inproceedings{ADHMS:11, author = {Atzmueller, Martin and Doerfel, Stephan and Hotho, Andreas and Mitzlaff, Folke and Stumme, Gerd}, booktitle = {Proc. Workshop on Mining Ubiquitous and Social Environments (MUSE 2011) at ECML/PKDD 2011}, interhash = {49e97def917e352ca21ab2e3eb7bd88a}, intrahash = {1fe037ea2712b205c564243d67840059}, title = {Face-to-Face Contacts during a Conference: Communities, Roles, and Key Players}, year = 2011 } @inproceedings{mitzlaff2011community, author = {Mitzlaff, Folke and Atzmueller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {Analysis of Social Media and Ubiquitous Data}, interhash = {1ef065a81ed836dfd31fcc4cd4da133b}, intrahash = {0f45e870093c053e6f41f54c14bda46b}, series = {LNAI}, title = {{Community Assessment using Evidence Networks}}, volume = 6904, year = 2011 } @inproceedings{mitzlaff2010community, abstract = {Community mining is a prominent approach for identifying (user) communities in social and ubiquitous contexts. While there are a variety of methods for community mining and detection, the effective evaluation and validation of the mined communities is usually non-trivial. Often there is no evaluation data at hand in order to validate the discovered groups. This paper proposes evidence networks using implicit information for the evaluation of communities. The presented evaluation approach is based on the idea of reconstructing existing social structures for the assessment and evaluation of a given clustering. We analyze and compare the presented evidence networks using user data from the real-world social bookmarking application BibSonomy. The results indicate that the evidence networks reflect the relative rating of the explicit ones very well.}, address = {Barcelona, Spain}, author = {Mitzlaff, Folke and Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the Workshop on Mining Ubiquitous and Social Environments (MUSE2010)}, interhash = {75fbc00000a1bd7ca5f93ca1d24d62c5}, intrahash = {34d79867b23f41ca2e9f481ee894630f}, title = {Community Assessment using Evidence Networks}, url = {http://www.kde.cs.uni-kassel.de/ws/muse2010}, year = 2010 } @book{noauthororeditoryahoo, abstract = {The past decade has witnessed the emergence of participatory Web and social media, bringing people together in many creative ways. Millions of users are playing, tagging, working, and socializing online, demonstrating new forms of collaboration, communication, and intelligence that were hardly imaginable just a short time ago. Social media also helps reshape business models, sway opinions and emotions, and opens up numerous possibilities to study human interaction and collective behavior in an unparalleled scale. This lecture, from a data mining perspective, introduces characteristics of social media, reviews representative tasks of computing with social media, and illustrates associated challenges. It introduces basic concepts, presents state-of-the-art algorithms with easy-to-understand examples, and recommends effective evaluation methods. In particular, we discuss graph-based community detection techniques and many important extensions that handle dynamic, heterogeneous networks in social media. We also demonstrate how discovered patterns of communities can be used for social media mining. The concepts, algorithms, and methods presented in this lecture can help harness the power of social media and support building socially-intelligent systems. This book is an accessible introduction to the study of \emph{community detection and mining in social media}. It is an essential reading for students, researchers, and practitioners in disciplines and applications where social media is a key source of data that piques our curiosity to understand, manage, innovate, and excel. This book is supported by additional materials, including lecture slides, the complete set of figures, key references, some toy data sets used in the book, and the source code of representative algorithms. The readers are encouraged to visit the book website for the latest information. Table of Contents: Social Media and Social Computing / Nodes, Ties, and Influence / Community Detection and Evaluation / Communities in Heterogeneous Networks / Social Media Mining }, author = {Tang‌, Lei and Liu‌, Huan}, doi = {10.2200/S00298ED1V01Y201009DMK003}, interhash = {717f8b976eec1dc934a3b84675456f25}, intrahash = {c4e1fa6bf2d52a237e5557640d87c970}, title = {Community Detection and Mining in Social Media}, url = {http://www.morganclaypool.com/doi/abs/10.2200/S00298ED1V01Y201009DMK003}, year = 2010 } @misc{Sonnenbichler2010, abstract = { Web 2.0 is transforming the internet: Information consumers become information producers and consumers at the same time. In virtual places like Facebook, Youtube, discussion boards and weblogs diversificated topics, groups and issues are propagated and discussed. Today an internet user is a member of lots of communities at different virtual places. "Real life" group membership and group behavior has been analyzed in science intensively in the last decades. Most interestingly, to our knowledge, user roles and behavior have not been adapted to the modern internet. In this work, we give a short overview of traditional community roles. We adapt those models and apply them to virtual online communities. We suggest a community membership life cycle model describing roles a user can take during his membership in a community. Our model is systematic and generic; it can be adapted to concrete communities in the web. The knowledge of a community's life cycle allows influencing the group structure: Stage transitions can be supported or harmed, e.g. to strengthen the binding of a user to a site and keep communities alive. }, author = {Sonnenbichler, Andreas C.}, interhash = {c244c29b978e6aa0b032a83597bd9744}, intrahash = {6b808f2988784442ca0f0ab2560f851b}, note = {cite arxiv:1006.4271 Comment: Presented at the International Network For Social Network Analysis (INSNA): Sunbelt Conference 2009, San Diego, California, USA. 9 pages, 6 figures}, title = {A Community Membership Life Cycle Model}, url = {http://arxiv.org/abs/1006.4271}, year = 2010 } @inproceedings{conf/icdm/TangWL09, author = {Tang, Lei and Wang, Xufei and Liu, Huan}, booktitle = {ICDM}, crossref = {conf/icdm/2009}, date = {2010-01-27}, editor = {Wang, Wei and Kargupta, Hillol and Ranka, Sanjay and Yu, Philip S. and Wu, Xindong}, ee = {http://doi.ieeecomputersociety.org/10.1109/ICDM.2009.20}, interhash = {e689d9e29e78d2c869896121ad37a772}, intrahash = {e54ea4c1636d8589d7a7d119291cb1ea}, isbn = {978-0-7695-3895-2}, pages = {503-512}, publisher = {IEEE Computer Society}, title = {Uncoverning Groups via Heterogeneous Interaction Analysis.}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.150.7384&rep=rep1&type=pdf}, year = 2009 } @misc{Leskovec2010, abstract = { Detecting clusters or communities in large real-world graphs such as large social or information networks is a problem of considerable interest. In practice, one typically chooses an objective function that captures the intuition of a network cluster as set of nodes with better internal connectivity than external connectivity, and then one applies approximation algorithms or heuristics to extract sets of nodes that are related to the objective function and that "look like" good communities for the application of interest. In this paper, we explore a range of network community detection methods in order to compare them and to understand their relative performance and the systematic biases in the clusters they identify. We evaluate several common objective functions that are used to formalize the notion of a network community, and we examine several different classes of approximation algorithms that aim to optimize such objective functions. In addition, rather than simply fixing an objective and asking for an approximation to the best cluster of any size, we consider a size-resolved version of the optimization problem. Considering community quality as a function of its size provides a much finer lens with which to examine community detection algorithms, since objective functions and approximation algorithms often have non-obvious size-dependent behavior. }, author = {Leskovec, Jure and Lang, Kevin J. and Mahoney, Michael W.}, interhash = {0e58de655596b2198f4a7001facd0c32}, intrahash = {410a9cbea51ea5dd3c56aad26a0e11b2}, note = {cite arxiv:1004.3539 }, title = {Empirical Comparison of Algorithms for Network Community Detection}, url = {http://arxiv.org/abs/1004.3539}, year = 2010 } @article{346336, address = {New York, NY, USA}, author = {Staab, S. and Angele, J. and Decker, S. and Erdmann, M. and Hotho, A. and Maedche, A. and Schnurr, H.-P. and Studer, R. and Sure, Y.}, doi = {http://dx.doi.org/10.1016/S1389-1286(00)00039-6}, interhash = {93e9f10176d9f06be1658ff793f7c2ea}, intrahash = {46b6d5dd3788371c719decd0c2d4897e}, issn = {1389-1286}, journal = {Comput. Netw.}, number = {1-6}, pages = {473--491}, publisher = {Elsevier North-Holland, Inc.}, title = {Semantic community Web portals}, url = {http://portal.acm.org/citation.cfm?id=346241.346336&coll=GUIDE&dl=GUIDE&CFID=7705918&CFTOKEN=32369470}, volume = 33, year = 2000 } @inproceedings{Detecting_Commmunities_via_Simultaneous_Clustering_of_Graphs_and_Folksonomies, author = {Java, Akshay and Joshi, Anupam and Finin, Tim}, booktitle = {WebKDD 2008 Workshop on Web Mining and Web Usage Analysis}, interhash = {acfec953843b168e61e2e167e29b4c3d}, intrahash = {645abd6b3191a2a6e844d7542651ed1c}, month = {August}, note = {To Appear}, title = {{Detecting Commmunities via Simultaneous Clustering of Graphs and Folksonomies}}, year = 2008 } @article{newman03fast, author = {Newman, M.E.J.}, interhash = {4493f03106eb8dd9db41c0ef3f667bb3}, intrahash = {56de7e6d214faebdbf2f2ef0fce09d7d}, journal = {Physical Review E}, month = {September}, title = {Fast algorithm for detecting community structure in networks}, url = {http://arxiv.org/abs/cond-mat/0309508}, volume = 69, year = 2003 } @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{1281269, address = {New York, NY, USA}, author = {Tantipathananandh, Chayant and Berger-Wolf, Tanya and Kempe, David}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, doi = {http://doi.acm.org/10.1145/1281192.1281269}, interhash = {9373b48866b4faa1941db0bee9265af0}, intrahash = {27a4fb58300979d4dbe94e75422418bd}, isbn = {978-1-59593-609-7}, location = {San Jose, California, USA}, pages = {717--726}, publisher = {ACM}, title = {A framework for community identification in dynamic social networks}, url = {http://portal.acm.org/citation.cfm?doid=1281192.1281269}, year = 2007 } @inproceedings{Approximating2008Java, abstract = {In many social media applications, a small fraction of the members are highly linked while most are sparsely connected to the network. Such a skewed distribution is sometimes referred to as the"long tail". Popular applications like meme trackers and content aggregators mine for information from only the popular blogs located at the head of this curve. On the other hand, the long tail contains large volumes of interesting information and niches. The question we address in this work is how best to approximate the community membership of entities in the long tail using only a small percentage of the entire graph structure. Our technique utilizes basic linear algebra manipulations and spectral methods. It has the advantage of quickly and efficiently finding a reasonable approximation of the community structure of the overall network. Such a method has significant applications in blog analysis engines as well as social media monitoring tools in general. }, author = {Java, Akshay and Joshi, Anupam and FininBook, Tim}, booktitle = {Proceedings of the Second International Conference on Weblogs and Social Media(ICWSM 2008)}, date = {2008 Abstract:}, interhash = {ede357e110fee8803dc181d262f30087}, intrahash = {386f36679c111f30e37ced272d5b355c}, publisher = {AAAI Press}, title = {Approximating the Community Structure of the Long Tail}, url = {http://ebiquity.umbc.edu/paper/html/id/381/Approximating-the-Community-Structure-of-the-Long-Tail}, year = 2008 } @inproceedings{conf/pkdd/CaiSHYH05, author = {Cai, Deng and Shao, Zheng and He, Xiaofei and Yan, Xifeng and Han, Jiawei}, booktitle = {PKDD}, crossref = {conf/pkdd/2005}, date = {2005-11-14}, editor = {Jorge, Alípio and Torgo, Luís and Brazdil, Pavel and Camacho, Rui and Gama, João}, ee = {http://dx.doi.org/10.1007/11564126_44}, interhash = {ffbc54eea27012bcd133f5b96fde010f}, intrahash = {6045c9e8efdcbe1578f1f769c6b9274b}, isbn = {3-540-29244-6}, pages = {445-452}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Community Mining from Multi-relational Networks.}, url = {http://dblp.uni-trier.de/db/conf/pkdd/pkdd2005.html#CaiSHYH05}, volume = 3721, year = 2005 } @article{clauset-2004-70, author = {Clauset, Aaron and Newman, M. E. J. and Moore, Cristopher}, interhash = {2c68e3c981a00380692a3b0b661d7cfd}, intrahash = {0ea285bfc0f5a46ffec8a213e5133ba6}, journal = {Physical Review E}, pages = 066111, title = {Finding community structure in very large networks}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cond-mat/0408187}, volume = 70, year = 2004 } @inproceedings{conf/kdd/BackstromHKL06, author = {Backstrom, Lars and Huttenlocher, Daniel P. and Kleinberg, Jon M. and Lan, Xiangyang}, booktitle = {KDD}, crossref = {conf/kdd/2006}, date = {2006-10-05}, editor = {Eliassi-Rad, Tina and Ungar, Lyle H. and Craven, Mark and Gunopulos, Dimitrios}, ee = {http://doi.acm.org/10.1145/1150402.1150412}, interhash = {a3cda51b88fd4ff49632bd6b393b5b6b}, intrahash = {d7f58740d7b63881ba4993d0a576be94}, isbn = {1-59593-339-5}, pages = {44-54}, publisher = {ACM}, title = {Group formation in large social networks: membership, growth, and evolution.}, url = {http://dblp.uni-trier.de/db/conf/kdd/kdd2006.html#BackstromHKL06}, year = 2006 } @inproceedings{jaeschke06wege, address = {Halle-Wittenberg}, author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Stumme, Gerd}, booktitle = {Proc. 18. Workshop Grundlagen von Datenbanken}, editor = {Braß, Stefan and Hinneburg, Alexander}, interhash = {59224b5889a24108434a9b5ecc6b0887}, intrahash = {2b6be3bd5daee7119973fcf69909956f}, month = {June}, pages = {80-84}, publisher = {Martin-Luther-Universität }, title = {Wege zur Entdeckung von Communities in Folksonomies}, year = 2006 } @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 } @article{reichardt-2004-93, author = {Reichardt, Joerg and Bornholdt, Stefan}, interhash = {d424bcc57ba04601143ad2aae05c2def}, intrahash = {7463a040a13328d06cf0f5b0f32ae85a}, journal = {Physical Review Letters}, pages = 218701, title = {Detecting fuzzy community structures in complex networks with a Potts model}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cond-mat/0402349}, volume = 93, year = 2004 }