@article{chen:058701, title = {Finding a Better Immunization Strategy}, author = {Yiping Chen and Gerald Paul and Shlomo Havlin and Fredrik Liljeros and H. Eugene Stanley}, journal = {Physical Review Letters}, number = 5, pages = 058701, publisher = {APS}, volume = 101, year = 2008, url = {http://link.aps.org/abstract/PRL/v101/e058701}, collaboration = {}, numpages = {4}, eid = {058701}, doi = {10.1103/PhysRevLett.101.058701}, description = {Finding a Better Immunization Strategy}, biburl = {http://www.bibsonomy.org/bibtex/23409d4e03990b0ff2a9704b665adf16e/hotho}, keywords = {graph toread clustering} } @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 = {hierarchical graph multiway multi coclustering clustering} } @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 = {networks community fast clustering algorithm} } @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 = {detection association community folksonomy *** del.icio.us rules clustering} } @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 = {code toread clustering SVM} } @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 = {graph detection community toread clustering} } @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 = {svd lsi toread clustering} } @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 = {text 2006 classification myown ol clustering} } @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 = {svd detection community toread clustering} } @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 classification clustering} } @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 = {bookmarking 2007 tagging social summerschool myown folksonomy sosbuch conceptual kdubiq clustering} } @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 2007 collaborative social myown folksonomy clustering} } @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 kmeans myown ontology gruppenbildung 2001 clustering} } @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 = {text 2002 myown ontology clustering} } @inproceedings{schmitz2006content, title = {Content Aggregation on Knowledge Bases using Graph Clustering}, address = {Budva, Montenegro}, author = {Christoph Schmitz and Andreas Hotho and Robert J\"aschke and Gerd Stumme}, booktitle = {Proceedings of the 3rd European Semantic Web Conference}, month = {June}, pages = {530-544}, publisher = {Springer}, series = {LNCS}, volume = 4011, year = 2006, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/schmitz2006sumarize_eswc.pdf}, isbn = {3-540-34544-2}, vgwort = {27}, biburl = {http://www.bibsonomy.org/bibtex/29a06428ec3bd72e3ea6c7a8f08e2bb85/hotho}, keywords = {content aggregation 2006 graph theory myown ontology clustering} } @inproceedings{cim04c, title = {Comparing Conceptual, Divise and Agglomerative Clustering for Learning Taxonomies from Text}, address = {Valencia, Spain}, author = {Philipp Cimiano and Andreas Hotho and Steffen Staab}, booktitle = {Proceedings of the European Conference on Artificial Intelligence (ECAI'04)}, editor = {Ramon L{\'o}pez de M{\'a}ntaras and Lorenza Saitta}, pages = {435-439}, publisher = {IOS Press}, year = 2004, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2004/ecai04.pdf}, file = {}, isbn = {1-58603-452-9}, biburl = {http://www.bibsonomy.org/bibtex/248d35aa9a4d727e221c90f959462b7b2/hotho}, keywords = {2004 myown learning taxonomies clustering} } @inproceedings{cim04a, title = {Clustering Ontologies from Text}, address = {Lisbon, Portugal}, author = {Philipp Cimiano and Andreas Hotho and Steffen Staab}, booktitle = {Proceedings of the Conference on Languages Resources and Evaluation (LREC)}, month = {MAY}, publisher = {ELRA - European Language Ressources Association}, year = 2004, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2004/lrec04.pdf}, file = {}, biburl = {http://www.bibsonomy.org/bibtex/23bc6e5a51dba862da1b7b3b6ac563370/hotho}, keywords = {text 2004 myown ol ontology clustering} } @inproceedings{hotho_pkdd03, title = {Explaining Text Clustering Results using Semantic Structures}, author = {A. Hotho and S. Staab and G. Stumme}, booktitle = {Proc. of the 7th European Conference on Principles and Practice of Knowledge Discovery in Databases, PKDD}, pages = {217-228}, series = {LNCS}, volume = 2838, year = 2003, file = {}, biburl = {http://www.bibsonomy.org/bibtex/2c1bb26aa5d4801542f832ffab70c82e5/hotho}, keywords = {visualization text 2003 myown SumSchool06 fca clustering} } @inproceedings{conf/iis/StaabH03, title = {Ontology-based Text Document Clustering.}, author = {Steffen Staab and Andreas Hotho}, booktitle = {Intelligent Information Processing and Web Mining, Proceedings of the International IIS: IIPWM'03 Conference held in Zakopane}, pages = {451-452}, year = 2003, url = {http://dblp.uni-trier.de/db/conf/iis/iis2003.html#StaabH03}, isbn = {3-540-00843-8}, description = {dblp}, biburl = {http://www.bibsonomy.org/bibtex/2d773061117a913428968cc99c6e1ec0f/hotho}, keywords = {text 2003 myown ontology clustering} } @article{kostoff, title = {Literature-related discovery (LRD): Potential treatments for cataracts}, author = {Ronald N. Kostoff}, journal = {Technological Forecasting and Social Change}, pages = {--}, volume = {In Press, Corrected Proof}, year = 2007, url = {http://www.sciencedirect.com/science/article/B6V71-4RDB8SC-9/2/8991fe8968a0ef12f22ed7e9ac9d7c4f}, description = {ScienceDirect - Technological Forecasting and Social Change : Literature-related discovery (LRD): Potential treatments for cataracts}, abstract = {Literature-related discovery (LRD) is the linking of two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge (i.e., potential discovery). The open discovery systems (ODS) component of LRD starts with a problem to be solved, and generates solutions to that problem through potential discovery. We have been using ODS LRD to identify potential treatments or preventative actions for challenging medical problems, among myriad other applications. This paper describes the second medical problem we addressed (cataract) using ODS LRD; the first problem addressed was Raynaud's Phenomenon (RP), and was described in the third paper of this Special Issue. Cataract was selected because it is ubiquitous globally, appears intractable to all forms of treatment other than surgical removal of cataracts, and is a major cause of blindness in many developing countries. The ODS LRD study had three objectives: a) identify non-drug non-surgical treatments that would 1) help prevent cataracts, or 2) reduce the progression rate of cataracts, or 3) stop the progression of cataracts, or 4) maybe even reverse the progression of cataracts; b) demonstrate that we could solve an ODS LRD problem with no prior knowledge of any results or prior work (unlike the case with the RP problem); c) determine whether large time savings in the discovery process were possible relative to the time required for conducting the RP study. To that end, we used the MeSH taxonomy of MEDLINE to restrict potential discoveries to selected semantic classes, as a substitute for the manually-intensive process used in the RP study to restrict potential discoveries to selected semantic classes. We also used additional semantic filtering to identify potential discovery within the selected semantic classes. All these goals were achieved. As will be shown, we generated large amounts of potential discovery in more than an order of magnitude less time than required for the RP study. We identified many non-drug non-surgical treatments that may be able to reduce or even stop the progression rate of cataracts. Time, and much testing, will determine whether this is possible. Finally, the methodology has been developed to the point where ODS LRD problems can be solved with no results or knowledge of any prior work.}, biburl = {http://www.bibsonomy.org/bibtex/2b9359f79985da9b9677340ffda849e74/hotho}, keywords = {mining text semantic retrieval toread discovery clustering} }