@inproceedings{schmitz2006content, abstract = {Recently, research projects such as PADLR and SWAP have developed tools like Edutella or Bibster, which are targeted at establishing peer-to-peer knowledge management (P2PKM) systems. In such a system, it is necessary to obtain provide brief semantic descriptions of peers, so that routing algorithms or matchmaking processes can make decisions about which communities peers should belong to, or to which peers a given query should be forwarded. This paper provides a graph clustering technique on knowledge bases for that purpose. Using this clustering, we can show that our strategy requires up to 58% fewer queries than the baselines to yield full recall in a bibliographic P2PKM scenario.}, address = {Heidelberg}, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, booktitle = {The Semantic Web: Research and Applications}, editor = {Sure, York and Domingue, John}, interhash = {d2ddbb8f90cd271dc18670e4c940ccfb}, intrahash = {1788c88e04112a4491f19dfffb8dc39e}, pages = {530-544}, publisher = {Springer}, series = {LNAI}, title = {Content Aggregation on Knowledge Bases using Graph Clustering}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006content.pdf}, volume = 4011, year = 2006 } @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{ls_leimeister, address = {Valencia, Spain}, author = {Duennebeil, S. and Sunyaev, A. and Blohm, I. and Leimeister, J. M. and Krcmar, H.}, booktitle = {3. International Conference on Health Informatics (HealthInf) 2010}, interhash = {c79ecc24f80f6572f79e40ef06342880}, intrahash = {6d8d3744dda9624c4ae1b10fed7b2e3e}, note = {163 (11-10)}, title = {Do German physicians want electronic health services? A characterization of potential adopters and rejectors in German ambulatory care}, url = {http://www.uni-kassel.de/fb7/ibwl/leimeister/pub/JML_150.pdf}, year = 2010 } @inproceedings{hotho03ontologies, address = {Melbourne, Florida}, author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd}, booktitle = {Proceedings of the 2003 IEEE International Conference on Data Mining}, comment = {alpha}, interhash = {b56c36d6d9c9ca9e6bd236a0f92415a5}, intrahash = {57a39c81cff1982dbefed529be934bee}, month = {November 19-22,}, pages = {541-544 (Poster}, publisher = {IEEE {C}omputer {S}ociety}, title = {Ontologies improve text document clustering}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003ontologies.pdf}, year = 2003 } @techreport{hotho03textclustering, abstract = {Text document clustering plays an important role in providing intuitive navigation and browsing mechanisms by organizing large amounts of information into a small number of meaningful clusters. Standard partitional or agglomerative clustering methods efficiently compute results to this end. However, the bag of words representation used for these clustering methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. Also, it is mostly left to the user to find out why a particular partitioning has been achieved, because it is only specified extensionally. In order to deal with the two problems, we integrate background knowledge into the process of clustering text documents. First, we preprocess the texts, enriching their representations by background knowledge provided in a core ontology — in our application Wordnet. Then, we cluster the documents by a partitional algorithm. Our experimental evaluation on Reuters newsfeeds compares clustering results with pre-categorizations of news. In the experiments, improvements of results by background knowledge compared to the baseline can be shown for many interesting tasks. Second, the clustering partitions the large number of documents to a relatively small number of clusters, which may then be analyzed by conceptual clustering. In our approach, we applied Formal Concept Analysis. Conceptual clustering techniques are known to be too slow for directly clustering several hundreds of documents, but they give an intensional account of cluster results. They allow for a concise description of commonalities and distinctions of different clusters. With background knowledge they even find abstractions like “food” (vs. specializations like “beef” or “corn”). Thus, in our approach, partitional clustering reduces first the size of the problem such that it becomes tractable for conceptual clustering, which then facilitates the understanding of the results.}, author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd}, comment = {alpha}, institution = {University of Karlsruhe, Institute AIFB}, interhash = {0bc7c3fc1273355f45c8970a7ea58f97}, intrahash = {61d58db419af0dbc3681432588219c3d}, title = {Text Clustering Based on Background Knowledge}, type = {Technical Report }, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003text.pdf}, volume = 425, year = 2003 } @inproceedings{hotho02conceptualclustering, author = {Hotho, A. and Stumme, G.}, booktitle = {Proc. Fachgruppentreffen Maschinelles Lernen (FGML 2002)}, comment = {alpha}, editor = {K\'okai, G. and Zeidler, J.}, interhash = {3dd3d4ce38d0de0ba8e167f8133cbb3e}, intrahash = {e253c44552a046fe90236274bcfeab13}, pages = {37-45}, title = {Conceptual Clustering of Text Clusters}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/FGML02.pdf}, year = 2002 } @inproceedings{hotho03wordnet, address = {Toronto}, author = {Hotho, A and Staab, S. and Stumme, G.}, booktitle = {Proc. SIGIR Semantic Web Workshop}, comment = {alpha}, interhash = {c2a9a89ce20cef90a1e78d34dc2c2afe}, intrahash = {04c7d86337d68e4ed9ae637029c43414}, title = {Wordnet improves text document clustering}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003wordnet.pdf}, year = 2003 } @inproceedings{hotho03explaining, abstract = {Common text clustering techniques offer rather poor capabilities for explaining to their users why a particular result has been achieved. They have the disadvantage that they do not relate semantically nearby terms and that they cannot explain how resulting clusters are related to each other. In this paper, we discuss a way of integrating a large thesaurus and the computation of lattices of resulting clusters into common text clustering in order to overcome these two problems. As its major result, our approach achieves an explanation using an appropriate level of granularity at the concept level as well as an appropriate size and complexity of the explaining lattice of resulting clusters.}, address = {Heidelberg}, author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd}, booktitle = {Knowledge Discovery in Databases: PKDD 2003, 7th European Conference on Principles and Practice of Knowledge Discovery in Databases}, comment = {alpha}, editor = {Lavra\v{c}, Nada and Gamberger, Dragan and Todorovski, Hendrik BlockeelLjupco}, interhash = {cf66183151a5d94a0941ac6d5089ae89}, intrahash = {53a943b6be4b34cf4e5329d0b58e99f6}, pages = {217-228}, publisher = {Springer}, series = {LNAI}, title = {Explaining Text Clustering Results using Semantic Structures}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003explaining.pdf}, volume = 2838, year = 2003 } @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{stumme01conceptualclustering, address = {Universität Dortmund 763}, author = {Stumme, G. and Taouil, R. and Bastide, Y. and Lakhal, L.}, booktitle = {Proc. GI-Fachgruppentreffen Maschinelles Lernen (FGML'01)}, editor = {Klinkenberg, R. and Rüping, S. and Fick, A. and Henze, N. and Herzog, C. and Molitor, R. and Schröder, O.}, interhash = {c99f2ae002435208c58f9244d298a10b}, intrahash = {f4ec21d5f63dbc213a3a6eae076c4b62}, month = {October}, title = {Conceptual Clustering with Iceberg Concept Lattices}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2001/FGML01.pdf}, year = 2001 } @inproceedings{schmitz2006content, abstract = {Recently, research projects such as PADLR and SWAP have developed tools like Edutella or Bibster, which are targeted at establishing peer-to-peer knowledge management (P2PKM) systems. In such a system, it is necessary to obtain provide brief semantic descriptions of peers, so that routing algorithms or matchmaking processes can make decisions about which communities peers should belong to, or to which peers a given query should be forwarded. This paper provides a graph clustering technique on knowledge bases for that purpose. Using this clustering, we can show that our strategy requires up to 58% fewer queries than the baselines to yield full recall in a bibliographic P2PKM scenario.}, address = {Berlin/Heidelberg}, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, booktitle = {The Semantic Web: Research and Applications}, doi = {10.1007/11762256_39}, editor = {Sure, York and Domingue, John}, interhash = {d2ddbb8f90cd271dc18670e4c940ccfb}, intrahash = {1788c88e04112a4491f19dfffb8dc39e}, isbn = {978-3-540-34544-2}, issn = {0302-9743}, month = jun, pages = {530--544}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Content Aggregation on Knowledge Bases using Graph Clustering}, url = {http://www.springerlink.com/content/u121v1827v286398/}, volume = 4011, year = 2006 } @incollection{bloehdorn2006learning, 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 -}, author = {Bloehdorn, Stephan and Cimiano, Philipp and Hotho, Andreas}, booktitle = {From Data and Information Analysis to Knowledge Engineering}, doi = {http://dx.doi.org/10.1007/3-540-31314-1_40}, interhash = {cf1af505b638677f00b3d3d7a5903199}, intrahash = {bc1d40cf4fd64780ecf712b1e40f31de}, isbn = {978-3-540-31313-7}, pages = {334--341}, publisher = {Springer Berlin Heidelberg}, title = {Learning Ontologies to Improve Text Clustering and Classification}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/2006-03-gfkl05-bloehdorn-etal-learning-ontologies.pdf}, year = 2006 } @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 } @inproceedings{658040, address = {Washington, DC, USA}, author = {Hotho, Andreas and Maedche, Alexander and Staab, Steffen}, booktitle = {ICDM '01: Proceedings of the 2001 IEEE International Conference on Data Mining}, interhash = {e2f356aeefc84fd73c9bcdc08392edf0}, intrahash = {a6803e87c5145d5f55d7bb1bab8dfd67}, isbn = {0-7695-1119-8}, pages = {607--608}, publisher = {IEEE Computer Society}, title = {Text Clustering Based on Good Aggregations}, url = {http://portal.acm.org/citation.cfm?id=658040}, year = 2001 } @inproceedings{hotho_fgml02, author = {Hotho, A. and Stumme, G.}, booktitle = {Proceedings of FGML Workshop}, interhash = {3dd3d4ce38d0de0ba8e167f8133cbb3e}, intrahash = {18fdbebb76d48feccf2dceed23f4cd74}, pages = {37-45}, publisher = {Special Interest Group of German Informatics Society (FGML --- Fachgruppe Maschinelles Lernen der GI e.V.)}, title = {Conceptual Clustering of Text Clusters}, url = {\url{http://www.aifb.uni-karlsruhe.de/WBS/aho/pub/tc_fca_2002_submit.pdf}}, year = 2002 } @inproceedings{schmitz2006content, address = {Budva, Montenegro}, author = {Schmitz, Christoph and Hotho, Andreas and J\"aschke, Robert and Stumme, Gerd}, booktitle = {Proceedings of the 3rd European Semantic Web Conference}, interhash = {940fa3c671c771cc9a644b3ecfef43cd}, intrahash = {9a06428ec3bd72e3ea6c7a8f08e2bb85}, isbn = {3-540-34544-2}, month = {June}, pages = {530-544}, publisher = {Springer}, series = {LNCS}, title = {Content Aggregation on Knowledge Bases using Graph Clustering}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/schmitz2006sumarize_eswc.pdf}, vgwort = {27}, volume = 4011, year = 2006 } @inproceedings{cim04c, address = {Valencia, Spain}, author = {Cimiano, Philipp and Hotho, Andreas and Staab, Steffen}, booktitle = {Proceedings of the European Conference on Artificial Intelligence (ECAI'04)}, editor = {de M{\'a}ntaras, Ramon L{\'o}pez and Saitta, Lorenza}, interhash = {5ebc73142f0c4d51a1037432435bab94}, intrahash = {48d35aa9a4d727e221c90f959462b7b2}, isbn = {1-58603-452-9}, pages = {435-439}, publisher = {IOS Press}, title = {Comparing Conceptual, Divise and Agglomerative Clustering for Learning Taxonomies from Text}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2004/ecai04.pdf}, year = 2004 } @inproceedings{cim04a, address = {Lisbon, Portugal}, author = {Cimiano, Philipp and Hotho, Andreas and Staab, Steffen}, booktitle = {Proceedings of the Conference on Languages Resources and Evaluation (LREC)}, interhash = {9374d126c328dab48f52854f73d6db4f}, intrahash = {3bc6e5a51dba862da1b7b3b6ac563370}, month = MAY, publisher = {ELRA - European Language Ressources Association}, title = {Clustering Ontologies from Text}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2004/lrec04.pdf}, year = 2004 } @inproceedings{hotho_pkdd03, author = {Hotho, A. and Staab, S. and Stumme, G.}, booktitle = {Proc. of the 7th European Conference on Principles and Practice of Knowledge Discovery in Databases, PKDD}, interhash = {cf66183151a5d94a0941ac6d5089ae89}, intrahash = {c1bb26aa5d4801542f832ffab70c82e5}, pages = {217-228}, series = {LNCS}, title = {Explaining Text Clustering Results using Semantic Structures}, volume = 2838, year = 2003 } @inproceedings{conf/iis/StaabH03, author = {Staab, Steffen and Hotho, Andreas}, booktitle = {Intelligent Information Processing and Web Mining, Proceedings of the International IIS: IIPWM'03 Conference held in Zakopane}, interhash = {dcb3c9710a44a43f9d8b17c5fc2b0f8c}, intrahash = {d773061117a913428968cc99c6e1ec0f}, isbn = {3-540-00843-8}, pages = {451-452}, title = {Ontology-based Text Document Clustering.}, url = {http://dblp.uni-trier.de/db/conf/iis/iis2003.html#StaabH03}, year = 2003 } @inproceedings{schmitz2006content, abstract = {Recently, research projects such as PADLR and SWAP have developed tools like Edutella or Bibster, which are targeted at establishing peer-to-peer knowledge management (P2PKM) systems. In such a system, it is necessary to obtain provide brief semantic descriptions of peers, so that routing algorithms or matchmaking processes can make decisions about which communities peers should belong to, or to which peers a given query should be forwarded. This paper provides a graph clustering technique on knowledge bases for that purpose. Using this clustering, we can show that our strategy requires up to 58% fewer queries than the baselines to yield full recall in a bibliographic P2PKM scenario.}, address = {Heidelberg}, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, booktitle = {The Semantic Web: Research and Applications}, editor = {Sure, York and Domingue, John}, interhash = {d2ddbb8f90cd271dc18670e4c940ccfb}, intrahash = {1788c88e04112a4491f19dfffb8dc39e}, pages = {530-544}, publisher = {Springer}, series = {LNAI}, title = {Content Aggregation on Knowledge Bases using Graph Clustering}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006content.pdf}, volume = 4011, year = 2006 } @inproceedings{hotho-ijcaiws2001, author = {Hotho, Andreas and Maedche, Alexander and Staab, Steffen}, booktitle = {Proc. of the Workshop ``Text Learning: Beyond Supervision'' at IJCAI 2001. Seattle, WA, USA, August 6, 2001}, interhash = {cce452c6e28cb3cfb99b3416457f1b24}, intrahash = {15a8cfc9a49b70812a55c76e597db7a5}, publihser = {Springer}, title = {Ontology-based Text Clustering}, year = 2001 } @article{hotho02ki, author = {Hotho, Andreas and Maedche, Alexander and Staab, Steffen}, interhash = {2b242ffbfb47a6b3a01584703ee31b9e}, intrahash = {b54e211028a75303d03dfdcce479428e}, journal = {K{\"{u}}nstliche Intelligenz (KI)}, number = 4, pages = {48-54}, title = {Text Clustering Based on Good Aggregations}, url = {http://www.aifb.uni-karlsruhe.de/WBS/aho/pub/Ontology_based_Text_Document_Clustering_2002.pdf}, volume = 16, year = 2002 } @techreport{hothoetal2003, author = {Hotho, A. and Staab, S. and Stumme, G.}, institution = {Institute AIFB, Universität Karlsruhe}, interhash = {0bc7c3fc1273355f45c8970a7ea58f97}, intrahash = {424a43b2ec8c865c1d66ca23440b1ac7}, note = {36 pages}, title = {Text Clustering Based on Background Knowledge}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/hotho_etal_techreport425.pdf}, year = 2003 } @inproceedings{hotho_sigir03, address = {Toronto, Canada}, author = {Hotho, A. and Staab, S. and Stumme, G.}, booktitle = {Proc. of the SIGIR 2003 Semantic Web Workshop}, interhash = {c2a9a89ce20cef90a1e78d34dc2c2afe}, intrahash = {b03e58ecb17c09f8c09d1fd93fb24f90}, title = {WordNet improves text document clustering}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/hothoetal_sigir_ws_sem_web.pdf}, year = 2003 } @inproceedings{hotho_icdm03, author = {Hotho, A. and Staab, S. and Stumme, G.}, booktitle = {Proc. of the ICDM 03, The 2003 IEEE International Conference on Data Mining}, interhash = {b56c36d6d9c9ca9e6bd236a0f92415a5}, intrahash = {8ce56ab228d021b2d7a37bc302bb9a0a}, pages = {541-544}, title = {Ontologies Improve Text Document Clustering}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/hothoa_icdm_poster03.pdf}, year = 2003 }