@article{keyhere,
  abstract = {The theory of concept (or Galois) lattices provides a simple and formal approach to conceptual clustering. In this paper we present GALOIS, a system that automates and applies this theory. The algorithm utilized by GALOIS to build a concept lattice is incremental and efficient, each update being done in time at most quadratic in the number of objects in the lattice. Also, the algorithm may incorporate background information into the lattice, and through clustering, extend the scope of the theory. The application we present is concerned with information retrieval via browsing, for which we argue that concept lattices may represent major support structures. We describe a prototype user interface for browsing through the concept lattice of a document-term relation, possibly enriched with a thesaurus of terms. An experimental evaluation of the system performed on a medium-sized bibliographic database shows good retrieval performance and a significant improvement after the introduction of background knowledge.
ER  -},
  author = {Carpineto, Claudio and Romano, Giovanni},
  interhash = {719ac1badf95acafafbd1487d82ae175},
  intrahash = {a53905954aeef0a80ec7424f978bca14},
  journal = {Machine Learning},
  month = {#aug#},
  number = 2,
  pages = {95--122},
  title = {A lattice conceptual clustering system and its application to browsing retrieval},
  url = {http://dx.doi.org/10.1007/BF00058654},
  volume = 24,
  year = 1996
}

@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
}

@unpublished{FalBar07,
  author = {Falkowski, Tanja and Barth, Anja},
  interhash = {72bc0bbc724d035ea119f793eb04f636},
  intrahash = {754a48202afdc98227bd53128524a77f},
  note = {Presented at The 4th conference on Applications of Social Network Analysis (ASNA)},
  title = {Density-based Temporal Graph Clustering for Subgroup Detection in Social Networks},
  year = 2007
}

@misc{noack08modularity,
  abstract = { Two natural and widely used representations for the community structure of networks are clusterings, which partition the vertex set into disjoint subsets, and layouts, which assign the vertices to positions in a metric space. This paper unifies prominent characterizations of layout quality and clustering quality, by showing that energy models of pairwise attraction and repulsion subsume Newman and Girvan's modularity measure. Layouts with optimal energy are relaxations of, and are thus consistent with, clusterings with optimal modularity, which is of practical relevance because both representations are complementary and often used together.},
  author = {Noack, Andreas},
  interhash = {a2442ee608964a82be06224fd90d54d3},
  intrahash = {0186031133dc122ffd6ff33ded32c911},
  title = {Modularity clustering is force-directed layout},
  url = {http://www.citebase.org/abstract?id=oai:arXiv.org:0807.4052},
  year = 2008
}

@inproceedings{FalBarSpi07,
  author = {Falkowski, Tanja and Barth, Anja and Spiliopoulou, Myra},
  booktitle = {In Proc. of the 2007 IEEE / WIC / ACM International Conference on Web Intelligence,},
  interhash = {abd9653fc405547fd263c72c5bc5ae88},
  intrahash = {c0f9b82222d0c9a0b1cb0a5fa41a735a},
  pages = {112-115},
  title = {DENGRAPH: A Density-based Community Detection Algorithm},
  url = {http://wwwiti.cs.uni-magdeburg.de/~tfalkows/publ/2007/WI_FalBarSpi07.pdf},
  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{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
}