@inproceedings{IfrimTW-ICML2005, title = {Learning Word-to-Concept Mappings for Automatic Text Classification}, address = {Bonn, Germany}, author = {Georgiana Ifrim and Martin Theobald and Gerhard Weikum}, booktitle = {Proceedings of the 22nd International Conference on Machine Learning - Learning in Web Search (LWS 2005)}, editor = {Luc De Raedt and Stefan Wrobel}, pages = {18--26}, year = 2005, url = {http://www.mpi-inf.mpg.de/~ifrim/publications/icml-lws05.pdf}, isbn = {1-59593-180-5}, description = {D5 MPI-INF Publications: Proceedings Article: Learning Word-to-Concept Mappings for Automatic Text Classification}, biburl = {http://www.bibsonomy.org/bibtex/257f8241941ed979455c3dbb90893020f/hotho}, keywords = {tc model text topic concept classification wordnet} } @article{voelker2008aeon, title = {AEON - An Approach to the Automatic Evaluation of Ontologies}, author = {Johanna Völker and Denny Vrandecic and York Sure and Andreas Hotho}, journal = {Journal of Applied Ontology}, note = {to appear}, year = 2008, url = {http://ontoware.org/projects/aeon/}, description = {Institut AIFB - Publikation: AEON - An Approach to the Automatic Evaluation of Ontologies}, biburl = {http://www.bibsonomy.org/bibtex/2ea55fe7088ef25cdf060d30d94a09e26/hotho}, keywords = {ml myown ontology evaluation automatic sw 2008} } @inproceedings{1102357, title = {Multi-way distributional clustering via pairwise interactions}, address = {New York, NY, USA}, author = {Ron Bekkerman and Ran El-Yaniv and Andrew McCallum}, booktitle = {ICML '05: Proceedings of the 22nd international conference on Machine learning}, pages = {41--48}, publisher = {ACM Press}, year = 2005, url = {http://www.cs.technion.ac.il/~rani/el-yaniv-papers/BekkermanEM05.pdf}, location = {Bonn, Germany}, isbn = {1-59593-180-5}, doi = {http://doi.acm.org/10.1145/1102351.1102357}, description = {Multi-way distributional clustering via pairwise interactions}, biburl = {http://www.bibsonomy.org/bibtex/2a5ac489feb7407a07570f6733665a6dd/hotho}, keywords = {clustering coclustering hierarchical multi multiway graph} } @article{newman03fast, title = {Fast algorithm for detecting community structure in networks}, author = {M.E.J. Newman}, journal = {Physical Review E}, month = {September}, volume = 69, year = 2003, url = {http://arxiv.org/abs/cond-mat/0309508}, biburl = {http://www.bibsonomy.org/bibtex/256de7e6d214faebdbf2f2ef0fce09d7d/hotho}, keywords = {community networks algorithm fast clustering} } @inproceedings{xin2008www, title = {Tag-based Social Interest Discovery}, author = {Xin Li and Lei Guo and Yihong E. Zhao}, booktitle = {Proceedings of the 17th International World Wide Web Conference}, pages = {675-684}, publisher = {ACM}, year = 2008, url = {http://www2008.org/papers/pdf/p675-liA.pdf}, 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.}, biburl = {http://www.bibsonomy.org/bibtex/242b4c94cff05ccef031235d661a7a77a/hotho}, keywords = {community *** clustering association detection del.icio.us folksonomy rules} } @inproceedings{cone2006, title = {Cone Cluster Labeling for Support Vector Clustering}, author = {Sei-Hyung Lee and Karen M. Daniels}, booktitle = {Proceedings of 6th SIAM Conference on Data Mining}, month = {May}, pages = {484–488}, year = 2006, url = {http://www.siam.org/meetings/sdm06/proceedings/046lees.pdf}, added = {2007-04-29 16:58:13 +0200}, modified = {2007-06-19 18:52:22 +0200}, description = {BibSonomy::edit bibtex}, biburl = {http://www.bibsonomy.org/bibtex/276d1018ba398695e454d20de302de6e6/hotho}, keywords = {toread clustering SVM code} } @inproceedings{1281269, title = {A framework for community identification in dynamic social networks}, address = {New York, NY, USA}, author = {Chayant Tantipathananandh and Tanya Berger-Wolf and David Kempe}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, pages = {717--726}, publisher = {ACM}, year = 2007, url = {http://portal.acm.org/citation.cfm?doid=1281192.1281269}, location = {San Jose, California, USA}, isbn = {978-1-59593-609-7}, doi = {http://doi.acm.org/10.1145/1281192.1281269}, description = {A framework for community identification in dynamic social networks}, biburl = {http://www.bibsonomy.org/bibtex/227a4fb58300979d4dbe94e75422418bd/hotho}, keywords = {community graph clustering detection toread} } @inproceedings{anti2008krause, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, author = {Beate Krause and Andreas Hotho and Gerd Stumme}, booktitle = {Proc. of the Fourth International Workshop on Adversarial Information Retrieval on the Web}, year = 2008, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, biburl = {http://www.bibsonomy.org/bibtex/203d349d70b578ca9ac3155f661151868/hotho}, keywords = {spam myown mining 2008 social classification bookmarking ml folksonomy dm} } @book{0387954333, title = {Text Mining. Predictive Methods for Analyzing Unstructured Information}, author = {Sholom M. Weiss and Nitin Indurkhya and T. Zhang}, edition = 1, publisher = {Springer, Berlin}, year = 2004, url = {http://www.amazon.de/gp/redirect.html%3FASIN=0387954333%26tag=ws%26lcode=xm2%26cID=2025%26ccmID=165953%26location=/o/ASIN/0387954333%253FSubscriptionId=13CT5CVB80YFWJEPWS02}, ean = {9780387954332}, asin = {0387954333}, isbn = {0387954333}, dewey = {006.312}, description = {Amazon.de: Text Mining. Predictive Methods for Analyzing Unstructured Information: Sholom M. Weiss,Nitin Indurkhya,T. Zhang: English Books}, biburl = {http://www.bibsonomy.org/bibtex/26ac07561b543e6033fd4c9811d0dccad/hotho}, keywords = {mining dm text tm software nlp} } @inproceedings{OsinskiSW04, title = {Lingo: Search Results Clustering Algorithm Based on Singular Value Decomposition}, author = {Stanislaw Osinski and Jerzy Stefanowski and Dawid Weiss}, booktitle = {Intelligent Information Systems}, crossref = {ConfIis2004}, pages = {359-368}, year = 2004, description = {DBLP Record 'conf/iis/OsinskiSW04'}, biburl = {http://www.bibsonomy.org/bibtex/240aba631c1ac8819bd64b0ee74bfdd1b/hotho}, keywords = {toread lsi clustering svd} } @article{bloehdorn2006learning, title = {Learning Ontologies to Improve Text Clustering and Classification}, author = {Stephan Bloehdorn and Philipp Cimiano and Andreas Hotho}, journal = {From Data and Information Analysis to Knowledge Engineering}, pages = {334--341}, year = 2006, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/2006-03-gfkl05-bloehdorn-etal-learning-ontologies.pdf}, doi = {http://dx.doi.org/10.1007/3-540-31314-1_40}, description = {SpringerLink - Book Chapter}, abstract = {Recent work has shown improvements in text clustering and classification tasks by integrating conceptual features extracted from ontologies. In this paper we present text mining experiments in the medical domain in which the ontological structures used are acquired automatically in an unsupervised learning process from the text corpus in question. We compare results obtained using the automatically learned ontologies with those obtained using manually engineered ones. Our results show that both types of ontologies improve results on text clustering and classification tasks, whereby the automatically acquired ontologies yield a improvement competitive with the manually engineered ones. ER -}, biburl = {http://www.bibsonomy.org/bibtex/2121bdc75ba2f61db089bac5f715a07ba/hotho}, keywords = {myown 2006 text ol clustering classification} } @inproceedings{Approximating2008Java, title = {Approximating the Community Structure of the Long Tail}, author = {Akshay Java and Anupam Joshi and Tim FininBook}, booktitle = {Proceedings of the Second International Conference on Weblogs and Social Media(ICWSM 2008)}, publisher = {AAAI Press}, year = 2008, url = {http://ebiquity.umbc.edu/paper/html/id/381/Approximating-the-Community-Structure-of-the-Long-Tail}, date = {2008 Abstract:}, description = {Approximating the Community Structure of the Long Tail}, 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. }, biburl = {http://www.bibsonomy.org/bibtex/2386f36679c111f30e37ced272d5b355c/hotho}, keywords = {toread clustering svd detection community} } @article{hotho2007mining, title = {Mining the World Wide Web}, author = {Andreas Hotho and Gerd Stumme}, journal = {Künstliche Intelligenz}, number = 3, pages = {5-8}, year = 2007, url = {http://kobra.bibliothek.uni-kassel.de/bitstream/urn:nbn:de:hebis:34-2008021320337/3/HothoStummeMiningWWW.pdf}, vgwort = {20}, biburl = {http://www.bibsonomy.org/bibtex/292d3a5fdd786086fa12787e3e350b6af/hotho}, keywords = {ir 2007 mining ki myown introduction ml web} } @inproceedings{baker98distributional, title = {Distributional clustering of words for text classification}, address = {Melbourne, AU}, author = {L. Douglas Baker and Andrew K. McCallum}, booktitle = {Proceedings of {SIGIR}-98, 21st {ACM} International Conference on Research and Development in Information Retrieval}, editor = {W. Bruce Croft and Alistair Moffat and Cornelis J. van Rijsbergen and Ross Wilkinson and Justin Zobel}, pages = {96--103}, publisher = {ACM Press, New York, US}, year = 1998, url = {citeseer.ist.psu.edu/baker98distributional.html}, biburl = {http://www.bibsonomy.org/bibtex/2e472dc4e61921ed15175756fcd9fea6a/hotho}, keywords = {text clustering classification} } @inproceedings{grahl2007clustering, title = {Conceptual Clustering of Social Bookmarking Sites}, address = {Graz, Austria}, author = {Miranda Grahl and Andreas Hotho and Gerd Stumme}, booktitle = {7th International Conference on Knowledge Management (I-KNOW '07)}, month = {SEP}, pages = {356-364}, publisher = {Know-Center}, year = 2007, issn = {0948-695x}, vgwort = {14}, 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.}, biburl = {http://www.bibsonomy.org/bibtex/2334d3ab11400c4a3ea3ed5b1e95c1855/hotho}, keywords = {sosbuch folksonomy social bookmarking tagging myown conceptual summerschool clustering kdubiq 2007} } @inproceedings{grahl07conceptualKdml, title = {Conceptual Clustering of Social Bookmark Sites}, author = {Miranda Grahl and Andreas Hotho and Gerd Stumme}, booktitle = {Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007)}, editor = {Alexander Hinneburg}, month = {sep}, pages = {50-54}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, year = 2007, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2007/kdml_recommender_final.pdf}, isbn = {978-3-86010-907-6}, vgwort = {14}, biburl = {http://www.bibsonomy.org/bibtex/26d5188d66564fe4ed7386e28868504de/hotho}, keywords = {bookmarking myown collaborative folksonomy social 2007 clustering} } @book{Berendt2007, title = {From Web to Social Web: Discovering and Deploying User and Content Profiles }, editor = {B. Berendt and A. Hotho and D. Mladenic and G. Semeraro}, publisher = {Springer}, series = {LNCS}, volume = 4736, year = 2007, url = {http://www.springer.com/dal/home?SGWID=1-102-22-173759307-0&changeHeader=true&referer=www.springeronline.com&SHORTCUT=www.springer.com/978-3-540-74950-9}, location = {Berlin, Germany}, isbn = {978-3-540-74950-9}, vgwort = {279}, date = {September 18, 2006 Series:}, description = {From Web to Social Web: Discovering and Deploying User and Cont... - Data Mi...Journals, Books & Online Media | Springer}, abstract = {This book constitutes the refereed proceedings of the Workshop on Web Mining, WebMine 2006, held in Berlin, Germany, September 18th, 2006. Topics included are data mining based on analysis of bloggers and tagging, web mining, XML mining and further techniques of knowledge discovery. The book is especially valuable for those interested in the aspects of the Social Web (Web 2.0) and its inherent dynamic and diversity of user-generated content.}, biburl = {http://www.bibsonomy.org/bibtex/28aa8d9bcbb5a5bb3fc480d1e53b27236/hotho}, keywords = {data social web myown tm 2007 mining dm} } @inproceedings{658040, title = {Text Clustering Based on Good Aggregations}, address = {Washington, DC, USA}, author = {Andreas Hotho and Alexander Maedche and Steffen Staab}, booktitle = {ICDM '01: Proceedings of the 2001 IEEE International Conference on Data Mining}, pages = {607--608}, publisher = {IEEE Computer Society}, year = 2001, url = {http://portal.acm.org/citation.cfm?id=658040}, isbn = {0-7695-1119-8}, description = {Text Clustering Based on Good Aggregations}, biburl = {http://www.bibsonomy.org/bibtex/2a6803e87c5145d5f55d7bb1bab8dfd67/hotho}, keywords = {tm text ontology 2001 myown gruppenbildung kmeans clustering} } @article{1276056, title = {Distributed feature extraction in a p2p setting: a case study}, address = {Amsterdam, The Netherlands, The Netherlands}, author = {Michael Wurst and Katharina Morik}, journal = {Future Gener. Comput. Syst.}, number = 1, pages = {69--75}, publisher = {Elsevier Science Publishers B. V.}, volume = 23, year = 2007, url = {http://portal.acm.org/citation.cfm?id=1276056}, issn = {0167-739X}, doi = {http://dx.doi.org/10.1016/j.future.2006.04.004}, description = {Distributed feature extraction in a p2p setting}, biburl = {http://www.bibsonomy.org/bibtex/2e5eba80e58b4532a3fd3bcf50994734e/hotho}, keywords = {music 2.0 p2p mining summerschool tagging web kdubiq dm} } @inproceedings{hotho_fgml02, title = {Conceptual Clustering of Text Clusters}, author = {A. Hotho and G. Stumme}, booktitle = {Proceedings of FGML Workshop}, pages = {37-45}, publisher = {Special Interest Group of German Informatics Society (FGML --- Fachgruppe Maschinelles Lernen der GI e.V.)}, year = 2002, url = {\url{http://www.aifb.uni-karlsruhe.de/WBS/aho/pub/tc_fca_2002_submit.pdf}}, file = {}, biburl = {http://www.bibsonomy.org/bibtex/218fdbebb76d48feccf2dceed23f4cd74/hotho}, keywords = {ontology 2002 text clustering myown} }