@article{mohammadSubmittedDistributional, author = {Mohammad, Saif and Hirst, Graeme}, title = {Distributional measures as proxies for semantic relatedness}, year = {Submitted for publication}, url = {http://ftp.cs.toronto.edu/pub/gh/Mohammad+Hirst-2005.pdf}, keywords = {distributional, measure, measures, relatedness, semantic, similarity, text} }

%0 = article %A = Mohammad, Saif and Hirst, Graeme %D = Submitted for publication %T = Distributional measures as proxies for semantic relatedness %U = http://ftp.cs.toronto.edu/pub/gh/Mohammad+Hirst-2005.pdf

@article{berendt2010bridging, author = {Berendt, Bettina and Hotho, Andreas and Stumme, Gerd}, title = {Bridging the Gap--Data Mining and Social Network Analysis for Integrating Semantic Web and Web 2.0}, journal = {Web Semantics: Science, Services and Agents on the World Wide Web}, year = {2010}, volume = {8}, number = {2-3}, pages = {95 - 96}, note = {Bridging the Gap--Data Mining and Social Network Analysis for Integrating Semantic Web and Web 2.0; The Future of Knowledge Dissemination: The Elsevier Grand Challenge for the Life Sciences}, url = {http://www.sciencedirect.com/science/article/B758F-4YXK4HW-1/2/4cb514565477c54160b5e6eb716c32d7}, doi = {DOI: 10.1016/j.websem.2010.04.008}, issn = {1570-8268}, keywords = {2010, data, introduction, itegpub, l3s, mining, myown, network, semantic, social, unik, web} }

%0 = article %A = Berendt, Bettina and Hotho, Andreas and Stumme, Gerd %D = 2010 %T = Bridging the Gap--Data Mining and Social Network Analysis for Integrating Semantic Web and Web 2.0 %U = http://www.sciencedirect.com/science/article/B758F-4YXK4HW-1/2/4cb514565477c54160b5e6eb716c32d7

Kooperative Verschlagwortungs- bzw. Social-Bookmarking-Systeme wie Delicious, Mister Wong oder auch unser eigenes System BibSonomy erfreuen sich immer größerer Beliebtheit und bilden einen zentralen Bestandteil des heutigen Web 2.0. In solchen Systemen erstellen Nutzer leichtgewichtige Begriffssysteme, sogenannte Folksonomies, die die Nutzerdaten strukturieren. Die einfache Bedienbarkeit, die Allgegenwärtigkeit, die ständige Verfügbarkeit, aber auch die Möglichkeit, Gleichgesinnte spontan in solchen Systemen zu entdecken oder sie schlicht als Informationsquelle zu nutzen, sind Gründe für ihren gegenwärtigen Erfolg. Der Artikel führt den Begriff Social Bookmarking ein und diskutiert zentrale Elemente (wie Browsing und Suche) am Beispiel von BibSonomy anhand typischer Arbeitsabläufe eines Wissenschaftlers. Wir beschreiben die Architektur von BibSonomy sowie Wege der Integration und Vernetzung von BibSonomy mit Content-Management-Systemen und Webauftritten. Der Artikel schließt mit Querbezügen zu aktuellen Forschungsfragen im Bereich Social Bookmarking.

@article{hotho2010publikationsmanagement, author = {Hotho, Andreas and Benz, Dominik and Eisterlehner, Folke and Jäschke, Robert and Krause, Beate and Schmitz, Christoph and Stumme, Gerd}, title = {Publikationsmanagement mit BibSonomy -- ein Social-Bookmarking-System für Wissenschaftler}, journal = {HMD -- Praxis der Wirtschaftsinformatik}, year = {2010}, volume = {Heft 271}, pages = {47-58}, issn = {1436-3011}, keywords = {2.0, 2010, info20, itegpub, l3s, management, myown, paper, semantic, tagging, web, web2.0}, abstract = {Kooperative Verschlagwortungs- bzw. Social-Bookmarking-Systeme wie Delicious, Mister Wong oder auch unser eigenes System BibSonomy erfreuen sich immer größerer Beliebtheit und bilden einen zentralen Bestandteil des heutigen Web 2.0. In solchen Systemen erstellen Nutzer leichtgewichtige Begriffssysteme, sogenannte Folksonomies, die die Nutzerdaten strukturieren. Die einfache Bedienbarkeit, die Allgegenwärtigkeit, die ständige Verfügbarkeit, aber auch die Möglichkeit, Gleichgesinnte spontan in solchen Systemen zu entdecken oder sie schlicht als Informationsquelle zu nutzen, sind Gründe für ihren gegenwärtigen Erfolg. Der Artikel führt den Begriff Social Bookmarking ein und diskutiert zentrale Elemente (wie Browsing und Suche) am Beispiel von BibSonomy anhand typischer Arbeitsabläufe eines Wissenschaftlers. Wir beschreiben die Architektur von BibSonomy sowie Wege der Integration und Vernetzung von BibSonomy mit Content-Management-Systemen und Webauftritten. Der Artikel schließt mit Querbezügen zu aktuellen Forschungsfragen im Bereich Social Bookmarking.} }

%0 = article %A = Hotho, Andreas and Benz, Dominik and Eisterlehner, Folke and Jäschke, Robert and Krause, Beate and Schmitz, Christoph and Stumme, Gerd %D = 2010 %T = Publikationsmanagement mit BibSonomy -- ein Social-Bookmarking-System für Wissenschaftler

Recent research provides evidence for the presence of emergent semantics in collaborative tagging systems. While several methods have been proposed, little is known about the factors that influence the evolution of semantic structures in these systems. A natural hypothesis is that the quality of the emergent semantics depends on the pragmatics of tagging: Users with certain usage patterns might contribute more to the resulting semantics than others. In this work, we propose several measures which enable a pragmatic differentiation of taggers by their degree of contribution to emerging semantic structures. We distinguish between categorizers, who typically use a small set of tags as a replacement for hierarchical classification schemes, and describers, who are annotating resources with a wealth of freely associated, descriptive keywords. To study our hypothesis, we apply semantic similarity measures to 64 different partitions of a real-world and large-scale folksonomy containing different ratios of categorizers and describers. Our results not only show that ‘verbose’ taggers are most useful for the emergence of tag semantics, but also that a subset containing only 40% of the most ‘verbose’ taggers can produce results that match and even outperform the semantic precision obtained from the whole dataset. Moreover, the results suggest that there exists a causal link between the pragmatics of tagging and resulting emergent semantics. This work is relevant for designers and analysts of tagging systems interested (i) in fostering the semantic development of their platforms, (ii) in identifying users introducing “semantic noise”, and (iii) in learning ontologies.

@inproceedings{koerner2010thinking, author = {Körner, Christian and Benz, Dominik and Strohmaier, Markus and Hotho, Andreas and Stumme, Gerd}, title = {Stop Thinking, start Tagging - Tag Semantics emerge from Collaborative Verbosity}, booktitle = {Proceedings of the 19th International World Wide Web Conference (WWW 2010)}, publisher = {ACM}, address = {Raleigh, NC, USA}, year = {2010}, url = {http://www.kde.cs.uni-kassel.de/benz/papers/2010/koerner2010thinking.pdf}, keywords = {bibsonomy, delicious, emerge, itegpub, l3s, myown, semantic, semantics, social, start, tagging, thinking, web}, abstract = {Recent research provides evidence for the presence of emergent semantics in collaborative tagging systems. While several methods have been proposed, little is known about the factors that influence the evolution of semantic structures in these systems. A natural hypothesis is that the quality of the emergent semantics depends on the pragmatics of tagging: Users with certain usage patterns might contribute more to the resulting semantics than others. In this work, we propose several measures which enable a pragmatic differentiation of taggers by their degree of contribution to emerging semantic structures. We distinguish between categorizers, who typically use a small set of tags as a replacement for hierarchical classification schemes, and describers, who are annotating resources with a wealth of freely associated, descriptive keywords. To study our hypothesis, we apply semantic similarity measures to 64 different partitions of a real-world and large-scale folksonomy containing different ratios of categorizers and describers. Our results not only show that ‘verbose’ taggers are most useful for the emergence of tag semantics, but also that a subset containing only 40% of the most ‘verbose’ taggers can produce results that match and even outperform the semantic precision obtained from the whole dataset. Moreover, the results suggest that there exists a causal link between the pragmatics of tagging and resulting emergent semantics. This work is relevant for designers and analysts of tagging systems interested (i) in fostering the semantic development of their platforms, (ii) in identifying users introducing “semantic noise”, and (iii) in learning ontologies.} }

%0 = inproceedings %A = Körner, Christian and Benz, Dominik and Strohmaier, Markus and Hotho, Andreas and Stumme, Gerd %B = Proceedings of the 19th International World Wide Web Conference (WWW 2010) %C = Raleigh, NC, USA %D = 2010 %I = ACM %T = Stop Thinking, start Tagging - Tag Semantics emerge from Collaborative Verbosity %U = http://www.kde.cs.uni-kassel.de/benz/papers/2010/koerner2010thinking.pdf

@inproceedings{eisterlehner2010visit, author = {Mitzlaff, Folke and Benz, Dominik and Stumme, Gerd and Hotho, Andreas}, title = {Visit me, click me, be my friend: An analysis of evidence networks of user relationships in Bibsonomy}, booktitle = {Proceedings of the 21st ACM conference on Hypertext and hypermedia}, address = {Toronto, Canada}, year = {2010}, keywords = {2010, analysis, bibsonomy, evidence, itegpub, l3s, links, myown, networks, semantic, sna, web} }

%0 = inproceedings %A = Mitzlaff, Folke and Benz, Dominik and Stumme, Gerd and Hotho, Andreas %B = Proceedings of the 21st ACM conference on Hypertext and hypermedia %C = Toronto, Canada %D = 2010 %T = Visit me, click me, be my friend: An analysis of evidence networks of user relationships in Bibsonomy

@book{berendt09knowledge, author = {?}, title = {Knowledge Discovery Enhanced with Semantic and Social Information}, publisher = {Springer}, address = {Heidelberg}, year = {2009 }, note = {(to appear)}, keywords = {2.0, discovery, information, knowledge, semantic, social, web, web2.0} }

%0 = book %A = ? %C = Heidelberg %D = 2009 %I = Springer %T = Knowledge Discovery Enhanced with Semantic and Social Information

@inproceedings{benz2009characterizing, author = {Benz, Dominik and Krause, Beate and Kumar, G. Praveen and Hotho, Andreas and Stumme, Gerd}, title = {Characterizing Semantic Relatedness of Search Query Terms}, booktitle = {Proceedings of the 1st Workshop on Explorative Analytics of Information Networks (EIN2009)}, address = {Bled, Slovenia}, year = {2009}, keywords = {2009, ecml, l3s, logsonomies, measures, myown, pkdd, relatedness, semantic, similarity} }

%0 = inproceedings %A = Benz, Dominik and Krause, Beate and Kumar, G. Praveen and Hotho, Andreas and Stumme, Gerd %B = Proceedings of the 1st Workshop on Explorative Analytics of Information Networks (EIN2009) %C = Bled, Slovenia %D = 2009 %T = Characterizing Semantic Relatedness of Search Query Terms

Social bookmarking systems allow users to organise collections of resources on the Web in a collaborative fashion. The increasing popularity of these systems as well as first insights into their emergent semantics have made them relevant to disciplines like knowledge extraction and ontology learning. The problem of devising methods to measure the semantic relatedness between tags and characterizing it semantically is still largely open. Here we analyze three measures of tag relatedness: tag co-occurrence, cosine similarity of co-occurrence distributions, and FolkRank, an adaptation of the PageRank algorithm to folksonomies. Each measure is computed on tags from a large-scale dataset crawled from the social bookmarking system del.icio.us. To provide a semantic grounding of our findings, a connection to WordNet (a semantic lexicon for the English language) is established by mapping tags into synonym sets of WordNet, and applying there well-known metrics of semantic similarity. Our results clearly expose different characteristics of the selected measures of relatedness, making them applicable to different subtasks of knowledge extraction such as synonym detection or discovery of concept hierarchies.

@inproceedings{cattuto08-semantic, author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, title = {Semantic Analysis of Tag Similarity Measures in Collaborative Tagging Systems}, booktitle = {Proceedings of the 3rd Workshop on Ontology Learning and Population (OLP3)}, address = {Patras, Greece}, year = {2008}, url = {http://olp.dfki.de/olp3/}, keywords = {2.0, 2008, collaborative, folksonomies, folksonomy, itegpub, myown, semantic, systems, tagging, web, web2.0}, abstract = {Social bookmarking systems allow users to organise collections of resources on the Web in a collaborative fashion. The increasing popularity of these systems as well as first insights into their emergent semantics have made them relevant to disciplines like knowledge extraction and ontology learning. The problem of devising methods to measure the semantic relatedness between tags and characterizing it semantically is still largely open. Here we analyze three measures of tag relatedness: tag co-occurrence, cosine similarity of co-occurrence distributions, and FolkRank, an adaptation of the PageRank algorithm to folksonomies. Each measure is computed on tags from a large-scale dataset crawled from the social bookmarking system del.icio.us. To provide a semantic grounding of our findings, a connection to WordNet (a semantic lexicon for the English language) is established by mapping tags into synonym sets of WordNet, and applying there well-known metrics of semantic similarity. Our results clearly expose different characteristics of the selected measures of relatedness, making them applicable to different subtasks of knowledge extraction such as synonym detection or discovery of concept hierarchies.} }

%0 = inproceedings %A = Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd %B = Proceedings of the 3rd Workshop on Ontology Learning and Population (OLP3) %C = Patras, Greece %D = 2008 %T = Semantic Analysis of Tag Similarity Measures in Collaborative Tagging Systems %U = http://olp.dfki.de/olp3/

Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For tasks like synonym detection and discovery of concept hierarchies, many researchers introduced measures of tag similarity. Even though most of these measures appear very natural, their design often seems to be rather ad hoc, and the underlying assumptions on the notion of similarity are not made explicit. A more systematic characterization and validation of tag similarity in terms of formal representations of knowledge is still lacking. Here we address this issue and analyze several measures of tag similarity: Each measure is computed on data from the social bookmarking system del.icio.us and a semantic grounding is provided by mapping pairs of similar tags in the folksonomy to pairs of synsets in Wordnet, where we use validated measures of semantic distance to characterize the semantic relation between the mapped tags. This exposes important features of the investigated similarity measures and indicates which ones are better suited in the context of a given semantic application.

@incollection{tagging-cattuto, author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems}, editor = {Sheth, Amit and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy and Thirunarayan, Krishnaprasad}, booktitle = {The Semantic Web - ISWC 2008}, series = {Lecture Notes in Computer Science}, journal = {The Semantic Web - ISWC 2008}, publisher = {Springer Berlin / Heidelberg}, year = {2008}, volume = {5318}, pages = {615--631}, url = {http://tagora-project.eu/wp-content/2009/09/cattuto_iswc2008.pdf}, doi = {10.1007/978-3-540-88564-139}, keywords = {2008, grounding, itegpub, l3s, literature, myown, pragmatic, relatedness, semantic, seminar, summer, tagging, wordnet}, abstract = {Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For tasks like synonym detection and discovery of concept hierarchies, many researchers introduced measures of tag similarity. Even though most of these measures appear very natural, their design often seems to be rather ad hoc, and the underlying assumptions on the notion of similarity are not made explicit. A more systematic characterization and validation of tag similarity in terms of formal representations of knowledge is still lacking. Here we address this issue and analyze several measures of tag similarity: Each measure is computed on data from the social bookmarking system del.icio.us and a semantic grounding is provided by mapping pairs of similar tags in the folksonomy to pairs of synsets in Wordnet, where we use validated measures of semantic distance to characterize the semantic relation between the mapped tags. This exposes important features of the investigated similarity measures and indicates which ones are better suited in the context of a given semantic application.} }

%0 = incollection %A = Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd %B = The Semantic Web - ISWC 2008 %D = 2008 %I = Springer Berlin / Heidelberg %T = Semantic Grounding of Tag Relatedness in Social Bookmarking Systems %U = http://tagora-project.eu/wp-content/2009/09/cattuto_iswc2008.pdf

Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For tasks
ke synonym detection and discovery of concept hierarchies, many researchers introduced measures of tag similarity. Eventhough most of these measures appear very natural, their design often seems to be rather ad hoc, and the underlying assumptionson the notion of similarity are not made explicit. A more systematic characterization and validation of tag similarity interms of formal representations of knowledge is still lacking. Here we address this issue and analyze several measures oftag similarity: Each measure is computed on data from the social bookmarking system del.icio.us and a semantic grounding isprovided by mapping pairs of similar tags in the folksonomy to pairs of synsets in Wordnet, where we use validated measuresof semantic distance to characterize the semantic relation between the mapped tags. This exposes important features of theinvestigated similarity measures and indicates which ones are better suited in the context of a given semantic application.

@inproceedings{cattuto2008semantic, author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems}, editor = {Sheth, Amit P. and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy W. and Thirunarayan, Krishnaprasad}, booktitle = {The Semantic Web -- ISWC 2008, Proc.Intl. Semantic Web Conference 2008}, series = {LNAI}, publisher = {Springer}, address = {Heidelberg}, year = {2008}, volume = {5318}, pages = {615--631}, url = {http://dx.doi.org/10.1007/978-3-540-88564-1_39}, keywords = {2008, grounding, iswc2008, itegpub, myown, relatedness, semantic, seminar2009, similarity, sw, tag, tagging, tagorapub}, abstract = {Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For tasks
ke synonym detection and discovery of concept hierarchies, many researchers introduced measures of tag similarity. Eventhough most of these measures appear very natural, their design often seems to be rather ad hoc, and the underlying assumptionson the notion of similarity are not made explicit. A more systematic characterization and validation of tag similarity interms of formal representations of knowledge is still lacking. Here we address this issue and analyze several measures oftag similarity: Each measure is computed on data from the social bookmarking system del.icio.us and a semantic grounding isprovided by mapping pairs of similar tags in the folksonomy to pairs of synsets in Wordnet, where we use validated measuresof semantic distance to characterize the semantic relation between the mapped tags. This exposes important features of theinvestigated similarity measures and indicates which ones are better suited in the context of a given semantic application.} }

%0 = inproceedings %A = Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd %B = The Semantic Web -- ISWC 2008, Proc.Intl. Semantic Web Conference 2008 %C = Heidelberg %D = 2008 %I = Springer %T = Semantic Grounding of Tag Relatedness in Social Bookmarking Systems %U = http://dx.doi.org/10.1007/978-3-540-88564-1_39

@book{Semantic2006Ackermann,, title = {Semantics, Web and Mining}, editor = {Ackermann, Markus and Berendt, Bettina and Grobelnik, Marko and Hotho, Andreas and Mladenic, Dunja and Semeraro, Giovanni and Spiliopoulou, Myra and Stumme, Gerd and Svatek, Vojtech and van Someren, Maarten}, publisher = {Springer}, address = {Heidelberg}, year = {2006}, url = {http://dx.doi.org/10.1007/11908678}, keywords = {2006, itegpub, l3s, mining, myown, semantic, semantics, web} }

%0 = book %C = Heidelberg %D = 2006 %I = Springer %T = Semantics, Web and Mining %U = http://dx.doi.org/10.1007/11908678

@proceedings{alani2006proceedings,, title = {Proceedings of the 2nd Workshop on Semantic Network Analysis}, editor = {Alani, Harith and Hoser, Bettina and Schmitz, Christoph and Stumme, Gerd}, year = {2006}, url = {http://www.kde.cs.uni-kassel.de/ws/sna2006/}, keywords = {2006, Network, Semantic, analysis, eswc, l3s, myown, nepomuk, network, proceedings, semantic, workshop} }

%0 = proceedings %D = 2006 %T = Proceedings of the 2nd Workshop on Semantic Network Analysis %U = http://www.kde.cs.uni-kassel.de/ws/sna2006/

@article{budanitsky06evaluating, author = {Budanitsky, Alexander and Hirst, Graeme}, title = {Evaluating WordNet-based Measures of Lexical Semantic Relatedness}, journal = {Computational Linguistics}, year = {2006}, volume = {32}, number = {1}, pages = {13-47}, url = {http://dblp.uni-trier.de/db/journals/coling/coling32.html#BudanitskyH06}, keywords = {WordNet, budanitsky, evaluating, evaluation, hirst, hurst, lexical, measures, semantic, similarity, study, user, wordnet} }

%0 = article %A = Budanitsky, Alexander and Hirst, Graeme %D = 2006 %T = Evaluating WordNet-based Measures of Lexical Semantic Relatedness %U = http://dblp.uni-trier.de/db/journals/coling/coling32.html#BudanitskyH06

A key argument for modeling knowledge in ontologies is the easy
-use and re-engineering of the knowledge. However, beside
nsistency checking, current ontology engineering tools provide
ly basic functionalities for analyzing ontologies. Since
tologies can be considered as (labeled, directed) graphs, graph
alysis techniques are a suitable answer for this need. Graph
alysis has been performed by sociologists for over 60 years, and
sulted in the vivid research area of Social Network Analysis
NA). While social network structures in general currently receive
gh attention in the Semantic Web community, there are only very
w SNA applications up to now, and virtually none for analyzing the
ructure of ontologies.

e illustrate in this paper the benefits of applying SNA to
tologies and the Semantic Web, and discuss which research topics
ise on the edge between the two areas. In particular, we discuss
w different notions of centrality describe the core content and
ructure of an ontology. From the rather simple notion of degree
ntrality over betweenness centrality to the more complex
genvector centrality based on Hermitian matrices, we illustrate
e insights these measures provide on two ontologies, which are
fferent in purpose, scope, and size.

@inproceedings{hoser2006semantic, author = {Hoser, Bettina and Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, title = {Semantic Network Analysis of Ontologies}, editor = {Sure, York and Domingue, John}, booktitle = {The Semantic Web: Research and Applications}, series = {LNAI}, publisher = {Springer}, address = {Heidelberg}, year = {2006}, volume = {4011}, pages = {514-529}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hoser2006semantic.pdf}, keywords = {2006, l3s, myown, nepomuk, ontology, semantic, sna, socialnetworkanalysis, sota, web}, abstract = {A key argument for modeling knowledge in ontologies is the easy
-use and re-engineering of the knowledge. However, beside
nsistency checking, current ontology engineering tools provide
ly basic functionalities for analyzing ontologies. Since
tologies can be considered as (labeled, directed) graphs, graph
alysis techniques are a suitable answer for this need. Graph
alysis has been performed by sociologists for over 60 years, and
sulted in the vivid research area of Social Network Analysis
NA). While social network structures in general currently receive
gh attention in the Semantic Web community, there are only very
w SNA applications up to now, and virtually none for analyzing the
ructure of ontologies.

e illustrate in this paper the benefits of applying SNA to
tologies and the Semantic Web, and discuss which research topics
ise on the edge between the two areas. In particular, we discuss
w different notions of centrality describe the core content and
ructure of an ontology. From the rather simple notion of degree
ntrality over betweenness centrality to the more complex
genvector centrality based on Hermitian matrices, we illustrate
e insights these measures provide on two ontologies, which are
fferent in purpose, scope, and size.} }

%0 = inproceedings %A = Hoser, Bettina and Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd %B = The Semantic Web: Research and Applications %C = Heidelberg %D = 2006 %I = Springer %T = Semantic Network Analysis of Ontologies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hoser2006semantic.pdf

@inproceedings{DBLP:conf/esws/NovacekS06, author = {Novácek, Vt and Smrz, Pavel}, title = {Empirical Merging of Ontologies - A Proposal of Universal Uncertainty Representation Framework.}, editor = {Sure, York and Domingue, John}, booktitle = {ESWC}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2006}, volume = {4011}, pages = {65-79}, isbn = {3-540-34544-2}, keywords = {2006, proceedings, web, ontology, eswc, conference, european, alignment, semantic} }

%0 = inproceedings %A = Novácek, Vt and Smrz, Pavel %B = ESWC %D = 2006 %I = Springer %T = Empirical Merging of Ontologies - A Proposal of Universal Uncertainty Representation Framework.

@book{pellegrini2006semantic,, title = {Semantic Web: Wege zur vernetzten Wissensgesellschaft}, editor = {Pellegrini, T. and Blumauer, A.}, publisher = {Springer}, address = {Heidelberg}, year = {2006}, keywords = {web, folksonomy, P2P, folksonomies, Wissensgesellschaft, semantic, wiss-org, Vernetzung} }

%0 = book %C = Heidelberg %D = 2006 %I = Springer %T = Semantic Web: Wege zur vernetzten Wissensgesellschaft

Wissensmanagement in zentralisierten Wissensbasen erfordert
nen hohen Aufwand für Erstellung und Wartung, und es entspricht nicht
mer den Anforderungen der Benutzer. Wir geben in diesem Kapitel einen Überblick
er zwei aktuelle Ansätze, die durch kollaboratives Wissensmanagement
ese Probleme lösen können. Im Peer-to-Peer-Wissensmanagement unterhalten
nutzer dezentrale Wissensbasen, die dann vernetzt werden können, um
dere Benutzer eigene Inhalte nutzen zu lassen. Folksonomies versprechen, die
ssensakquisition so einfach wie möglich zu gestalten und so viele Benutzer in
n Aufbau und die Pflege einer gemeinsamen Wissensbasis einzubeziehen.

@inbook{schmitz2006kollaboratives, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, title = {Kollaboratives Wissensmanagement}, editor = {Pellegrini, Tassilo and Blumauer, Andreas}, booktitle = {Semantic Web - Wege zur vernetzten Wissensgesellschaft}, publisher = {Springer}, year = {2006}, pages = {273-290}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006kollaboratives.pdf}, isbn = {3-540-29324-8}, keywords = {2006, Wissensmanagement, collaborative, folksonomy, knowledge, l3s, management, myown, nepomuk, p2p, semantic, web, wissensmanagement}, abstract = {Wissensmanagement in zentralisierten Wissensbasen erfordert
nen hohen Aufwand für Erstellung und Wartung, und es entspricht nicht
mer den Anforderungen der Benutzer. Wir geben in diesem Kapitel einen Überblick
er zwei aktuelle Ansätze, die durch kollaboratives Wissensmanagement
ese Probleme lösen können. Im Peer-to-Peer-Wissensmanagement unterhalten
nutzer dezentrale Wissensbasen, die dann vernetzt werden können, um
dere Benutzer eigene Inhalte nutzen zu lassen. Folksonomies versprechen, die
ssensakquisition so einfach wie möglich zu gestalten und so viele Benutzer in
n Aufbau und die Pflege einer gemeinsamen Wissensbasis einzubeziehen.} }

%0 = inbook %A = Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd %B = Semantic Web - Wege zur vernetzten Wissensgesellschaft %D = 2006 %I = Springer %T = Kollaboratives Wissensmanagement %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006kollaboratives.pdf

Social bookmark tools are rapidly emerging on the Web. In such
stems users are setting up lightweight conceptual structures
lled folksonomies. These systems provide currently relatively few
ructure. We discuss in this paper, how association rule mining
n be adopted to analyze and structure folksonomies, and how the results can be used
r ontology learning and supporting emergent semantics. We
monstrate our approach on a large scale dataset stemming from an
line system.

@inproceedings{schmitz2006mining, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, title = {Mining Association Rules in Folksonomies}, editor = {Batagelj, V. and Bock, H.-H. and Ferligoj, A. and Žiberna, A.}, booktitle = {Data Science and Classification. Proceedings of the 10th IFCS Conf.}, series = {Studies in Classification, Data Analysis, and Knowledge Organization}, publisher = {Springer}, address = {Heidelberg}, year = {2006}, pages = {261--270}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006mining.pdf}, keywords = {2006, analysis, fca, folksonomies, folksonomy, l3s, myown, nepomuk, network, semantic}, abstract = {Social bookmark tools are rapidly emerging on the Web. In such
stems users are setting up lightweight conceptual structures
lled folksonomies. These systems provide currently relatively few
ructure. We discuss in this paper, how association rule mining
n be adopted to analyze and structure folksonomies, and how the results can be used
r ontology learning and supporting emergent semantics. We
monstrate our approach on a large scale dataset stemming from an
line system.} }

%0 = inproceedings %A = Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd %B = Data Science and Classification. Proceedings of the 10th IFCS Conf. %C = Heidelberg %D = 2006 %I = Springer %T = Mining Association Rules in Folksonomies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006mining.pdf

@inproceedings{DBLP:conf/esws/SerafiniZSB06, author = {Serafini, Luciano and Zanobini, Stefano and Sceffer, Simone and Bouquet, Paolo}, title = {Matching Hierarchical Classifications with Attributes.}, editor = {Sure, York and Domingue, John}, booktitle = {ESWC}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2006}, volume = {4011}, pages = {4-18}, isbn = {3-540-34544-2}, keywords = {2006, proceedings, web, ontology, eswc, conference, european, alignment, semantic} }

%0 = inproceedings %A = Serafini, Luciano and Zanobini, Stefano and Sceffer, Simone and Bouquet, Paolo %B = ESWC %D = 2006 %I = Springer %T = Matching Hierarchical Classifications with Attributes.

Wikipedia provides a knowledge base for computing word relatedness in a more structured fashion than a search engine and with more coverage than WordNet. In this work we present experiments on using Wikipedia for computing semantic relatedness and compare it to WordNet on various benchmarking datasets. Existing relatedness measures perform better using Wikipedia than a baseline given by Google counts, and we show that Wikipedia outperforms WordNet when applied to the largest available dataset designed for that purpose. The best results on this dataset are obtained by integrating Google, WordNet and Wikipedia based measures. We also show that including Wikipedia improves the performance of an NLP application processing naturally occurring texts.

@inproceedings{Strube:2006:WCS:1597348.1597414, author = {Strube, Michael and Ponzetto, Simone Paolo}, title = {WikiRelate! computing semantic relatedness using wikipedia}, booktitle = {proceedings of the 21st national conference on Artificial intelligence - Volume 2}, series = {AAAI'06}, publisher = {AAAI Press}, year = {2006}, pages = {1419--1424}, url = {http://dl.acm.org/citation.cfm?id=1597348.1597414}, isbn = {978-1-57735-281-5}, keywords = {measure, relatedness, semantic, similarity, wikipedia, wordnet}, abstract = {Wikipedia provides a knowledge base for computing word relatedness in a more structured fashion than a search engine and with more coverage than WordNet. In this work we present experiments on using Wikipedia for computing semantic relatedness and compare it to WordNet on various benchmarking datasets. Existing relatedness measures perform better using Wikipedia than a baseline given by Google counts, and we show that Wikipedia outperforms WordNet when applied to the largest available dataset designed for that purpose. The best results on this dataset are obtained by integrating Google, WordNet and Wikipedia based measures. We also show that including Wikipedia improves the performance of an NLP application processing naturally occurring texts.} }

%0 = inproceedings %A = Strube, Michael and Ponzetto, Simone Paolo %B = proceedings of the 21st national conference on Artificial intelligence - Volume 2 %D = 2006 %I = AAAI Press %T = WikiRelate! computing semantic relatedness using wikipedia %U = http://dl.acm.org/citation.cfm?id=1597348.1597414

SemanticWeb Mining aims at combining the two fast-developing research areas SemanticWeb andWeb Mining.
is survey analyzes the convergence of trends from both areas: an increasing number of researchers is working on
proving the results ofWeb Mining by exploiting semantic structures in theWeb, and they make use ofWeb Mining
chniques for building the Semantic Web. Last but not least, these techniques can be used for mining the Semantic
b itself.
e Semantic Web is the second-generation WWW, enriched by machine-processable information which supports
e user in his tasks. Given the enormous size even of today’s Web, it is impossible to manually enrich all of
ese resources. Therefore, automated schemes for learning the relevant information are increasingly being used.
b Mining aims at discovering insights about the meaning of Web resources and their usage. Given the primarily
ntactical nature of the data being mined, the discovery of meaning is impossible based on these data only. Therefore,
rmalizations of the semantics of Web sites and navigation behavior are becoming more and more common.
rthermore, mining the Semantic Web itself is another upcoming application. We argue that the two areas Web
ning and Semantic Web need each other to fulfill their goals, but that the full potential of this convergence is not
t realized. This paper gives an overview of where the two areas meet today, and sketches ways of how a closer
tegration could be profitable.

@article{jws2006Semantic, author = {Stumme, Gerd and Hotho, Andreas and Berendt, Bettina}, title = {Semantic Web Mining - State of the Art and Future Directions}, journal = {Journal of Web Semantics}, publisher = {Elsevier}, year = {2006}, volume = {4}, number = {2}, pages = {124-143}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/stumme2006semantic.pdf}, keywords = {2006, l3s, mining, myown, semantic, sota, survey, web}, abstract = {SemanticWeb Mining aims at combining the two fast-developing research areas SemanticWeb andWeb Mining.This survey analyzes the convergence of trends from both areas: an increasing number of researchers is working onimproving the results ofWeb Mining by exploiting semantic structures in theWeb, and they make use ofWeb Miningtechniques for building the Semantic Web. Last but not least, these techniques can be used for mining the SemanticWeb itself.The Semantic Web is the second-generation WWW, enriched by machine-processable information which supportsthe user in his tasks. Given the enormous size even of today’s Web, it is impossible to manually enrich all ofthese resources. Therefore, automated schemes for learning the relevant information are increasingly being used.Web Mining aims at discovering insights about the meaning of Web resources and their usage. Given the primarilysyntactical nature of the data being mined, the discovery of meaning is impossible based on these data only. Therefore,formalizations of the semantics of Web sites and navigation behavior are becoming more and more common.Furthermore, mining the Semantic Web itself is another upcoming application. We argue that the two areas WebMining and Semantic Web need each other to fulfill their goals, but that the full potential of this convergence is notyet realized. This paper gives an overview of where the two areas meet today, and sketches ways of how a closerintegration could be profitable.} }

%0 = article %A = Stumme, Gerd and Hotho, Andreas and Berendt, Bettina %D = 2006 %I = Elsevier %T = Semantic Web Mining - State of the Art and Future Directions %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/stumme2006semantic.pdf

@proceedings{DBLP:conf/esws/2006,, title = {The Semantic Web: Research and Applications, 3rd European
Semantic Web Conference, ESWC 2006, Budva, Montenegro, June
11-14, 2006, Proceedings}, editor = {Sure, York and Domingue, John}, booktitle = {ESWC}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2006}, volume = {4011}, isbn = {3-540-34544-2}, keywords = {2006, proceedings, web, springer, lnai, eswc, conference, european, semantic} }

%0 = proceedings %B = ESWC %D = 2006 %I = Springer %T = The Semantic Web: Research and Applications, 3rd European
Semantic Web Conference, ESWC 2006, Budva, Montenegro, June
11-14, 2006, Proceedings

@inproceedings{DBLP:conf/esws/AssemMMS06, author = {van Assem, Mark and Malaisé, Véronique and Miles, Alistair and Schreiber, Guus}, title = {A Method to Convert Thesauri to SKOS.}, editor = {Sure, York and Domingue, John}, booktitle = {ESWC}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2006}, volume = {4011}, pages = {95-109}, isbn = {3-540-34544-2}, keywords = {2006, proceedings, web, engineering, ontology, eswc, conference, european, semantic} }

%0 = inproceedings %A = van Assem, Mark and Malaisé, Véronique and Miles, Alistair and Schreiber, Guus %B = ESWC %D = 2006 %I = Springer %T = A Method to Convert Thesauri to SKOS.

@inproceedings{berendt05semantic, author = {Berendt, Bettina and Hotho, Andreas and Stumme, Gerd}, title = {Semantic Web Mining and the Representation, Analysis, and Evolution of Web Space}, editor = {Svatek, Vojtech and Snasel, Vaclav}, booktitle = {Proc. of the 1st Intl. Workshop on Representation and Analysis of Web Space}, publisher = {Technical University of Ostrava}, year = {2005}, pages = {1-16}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2005/berendt2005semantic.pdf}, isbn = {80-248-0864-1}, keywords = {2005, itegpub, l3s, mining, myown, semantic, web} }

%0 = inproceedings %A = Berendt, Bettina and Hotho, Andreas and Stumme, Gerd %B = Proc. of the 1st Intl. Workshop on Representation and Analysis of Web Space %D = 2005 %I = Technical University of Ostrava %T = Semantic Web Mining and the Representation, Analysis, and Evolution of Web Space %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2005/berendt2005semantic.pdf

@proceedings{stumme05semanticnetworkanalysis,, title = {Proceedings of the First Workshop on Semantic Network Analysis }, editor = {Stumme, Gerd and Hoser, Bettina and Schmitz, Christoph and Alani, Harith}, publisher = {CEUR Proceedings}, address = {Aachen}, year = {2005}, url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-171/}, issn = {1613-0073}, keywords = {2005, analysis, iswc, itegpub, l3s, myown, nepomuk, network, proceedings, semantic, semna, sna, workshop} }

%0 = proceedings %C = Aachen %D = 2005 %I = CEUR Proceedings %T = Proceedings of the First Workshop on Semantic Network Analysis %U = http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-171/

The purpose of Web mining is to develop methods and systems for discovering models of objects and processes on the World Wide Web and for web-based systems that show adaptive performance. Web Mining integrates three parent areas: Data Mining (we use this term here also for the closely related areas of Machine Learning and Knowledge Discovery), Internet technology and World Wide Web, and for the more recent Semantic Web. The World Wide Web has made an enormous amount of information electronically accessible. The use of email, news and markup languages like HTML allow users to publish and read documents at a world-wide scale and to communicate via chat connections, including information in the form of images and voice records. The HTTP protocol that enables access to documents over the network via Web browsers created an immense improvement in communication and access to information. For some years these possibilities were used mostly in the scientific world but recent years have seen an immense growth in popularity, supported by the wide availability of computers and broadband communication. The use of the internet for other tasks than finding information and direct communication is increasing, as can be seen from the interest in ldquoe-activitiesrdquo such as e-commerce, e-learning, e-government, e-science.

@inproceedings{berendt2004roadmap, author = {Berendt, Bettina and Hotho, Andreas and Mladenic, Dunja and van Someren, Maarten and Spiliopoulou, Myra and Stumme, Gerd}, title = {A Roadmap for Web Mining: From Web to Semantic Web.}, editor = {Berendt, Bettina and Hotho, Andreas and Mladenic, Dunja and van Someren, Maarten and Spiliopoulou, Myra and Stumme, Gerd}, booktitle = {Web Mining: From Web to Semantic Web}, publisher = {Springer}, address = {Heidelberg}, year = {2004}, volume = {3209}, pages = {1-22}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2004/berendt2004roadmap.pdf}, keywords = {2004, ecml, ewmf, itegpub, l3s, mining, myown, pkdd, proceedings, roadmap, semantic, web, workshop}, abstract = {The purpose of Web mining is to develop methods and systems for discovering models of objects and processes on the World Wide Web and for web-based systems that show adaptive performance. Web Mining integrates three parent areas: Data Mining (we use this term here also for the closely related areas of Machine Learning and Knowledge Discovery), Internet technology and World Wide Web, and for the more recent Semantic Web. The World Wide Web has made an enormous amount of information electronically accessible. The use of email, news and markup languages like HTML allow users to publish and read documents at a world-wide scale and to communicate via chat connections, including information in the form of images and voice records. The HTTP protocol that enables access to documents over the network via Web browsers created an immense improvement in communication and access to information. For some years these possibilities were used mostly in the scientific world but recent years have seen an immense growth in popularity, supported by the wide availability of computers and broadband communication. The use of the internet for other tasks than finding information and direct communication is increasing, as can be seen from the interest in ldquoe-activitiesrdquo such as e-commerce, e-learning, e-government, e-science.} }

%0 = inproceedings %A = Berendt, Bettina and Hotho, Andreas and Mladenic, Dunja and van Someren, Maarten and Spiliopoulou, Myra and Stumme, Gerd %B = Web Mining: From Web to Semantic Web %C = Heidelberg %D = 2004 %I = Springer %T = A Roadmap for Web Mining: From Web to Semantic Web. %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2004/berendt2004roadmap.pdf

Semantic Web Mining aims at combining the two fast-developing
search areas Semantic Web and Web Mining.
b Mining aims at discovering insights about the meaning of Web
sources and their usage. Given the primarily syntactical nature
data Web mining operates on, the discovery of meaning is
possible based on these data only. Therefore, formalizations of
e semantics of Web resources and navigation behavior are
creasingly being used. This fits exactly with the aims of the
mantic Web: the Semantic Web enriches the WWW by
chine-processable information which supports the user in his
sks. In this paper, we discuss the interplay of the Semantic Web
th Web Mining, with a specific focus on usage mining.

@incollection{berendt04usage, author = {Berendt, Bettina and Hotho, Andreas and Stumme, Gerd}, title = {Usage Mining for and on the Semantic Web}, editor = {Kargupta, Hillol and Joshi, Anupam and Sivakumar, Krishnamoorthy and Yesha, Yelena}, booktitle = {Data Mining Next Generation Challenges and Future Directions}, publisher = {AAAI Press}, address = {Boston}, year = {2004}, pages = {461-481}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2004/berendt04usage.pdf}, isbn = {0-262-61203-8}, keywords = {2004, itegpub, l3s, mining, myown, semantic, usage, web}, abstract = {Semantic Web Mining aims at combining the two fast-developing
search areas Semantic Web and Web Mining.
b Mining aims at discovering insights about the meaning of Web
sources and their usage. Given the primarily syntactical nature
data Web mining operates on, the discovery of meaning is
possible based on these data only. Therefore, formalizations of
e semantics of Web resources and navigation behavior are
creasingly being used. This fits exactly with the aims of the
mantic Web: the Semantic Web enriches the WWW by
chine-processable information which supports the user in his
sks. In this paper, we discuss the interplay of the Semantic Web
th Web Mining, with a specific focus on usage mining.} }

%0 = incollection %A = Berendt, Bettina and Hotho, Andreas and Stumme, Gerd %B = Data Mining Next Generation Challenges and Future Directions %C = Boston %D = 2004 %I = AAAI Press %T = Usage Mining for and on the Semantic Web %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2004/berendt04usage.pdf

@proceedings{berendt2004web,, title = {Web Mining: From Web to Semantic Web, First European Web
Mining Forum, EMWF 2003, Cavtat-Dubrovnik, Croatia, September
22, 2003, Revised Selected and Invited Papers}, editor = {Berendt, Bettina and Hotho, Andreas and Mladenic, Dunja and van Someren, Maarten and Spiliopoulou, Myra and Stumme, Gerd}, series = {LNAI}, publisher = {Springer}, address = {Heidelberg}, year = {2004}, volume = {3209}, note = {http://km.aifb.uni-karlsruhe.de/ws/ewmf03/}, url = {http://springerlink.metapress.com/content/unvvag26dttf/}, isbn = {3-540-23258-3}, keywords = {2004, ecml, itegpub, l3s, mining, myown, pkdd, proceedings, semantic, web, workshop} }

%0 = proceedings %C = Heidelberg %D = 2004 %I = Springer %T = Web Mining: From Web to Semantic Web, First European Web
Mining Forum, EMWF 2003, Cavtat-Dubrovnik, Croatia, September
22, 2003, Revised Selected and Invited Papers %U = http://springerlink.metapress.com/content/unvvag26dttf/

@inproceedings{tane04semantic, author = {Tane, Julien and Schmitz, Christoph and Stumme, Gerd}, title = {Semantic resource management for the web: an e-learning application}, booktitle = {Proc. 13th International World Wide Web Conference (WWW 2004)}, year = {2004}, pages = {1-10}, url = {http://www.www2004.org/proceedings/docs/2p1.pdf}, keywords = {2004, application, courseware, crawler, e-learning, eLearning, edutella, fca, itegpub, l3s, learning, myown, p2p, semantic, watchdog, web} }

%0 = inproceedings %A = Tane, Julien and Schmitz, Christoph and Stumme, Gerd %B = Proc. 13th International World Wide Web Conference (WWW 2004) %D = 2004 %T = Semantic resource management for the web: an e-learning application %U = http://www.www2004.org/proceedings/docs/2p1.pdf

The paper describes a set of approaches for representing and
cessing information within a semantically structured information
rtal, while offering the possibility to integrate own
formation. It discusses research performed within the project
emantic Methods and Tools for Information Portals (SemIPort)'.
particular, it focuses on (1) the development of scalable
oring, processing and querying methods for semantic data, (2)
sualization and browsing of complex data inventories, (3)
rsonalization and agent-based interaction, and (4) the
hancement of web mining approaches for use within a
mantics-based portal.

@inproceedings{agarwal03semantic, author = {Agarwal, Sudhir and Fankhauser, Peter and Gonzalez-Ollala, Jorge and Hartmann, Jens and Hollfelder, Silvia and Jameson, Anthony and Klink, Stefan and Lehti, Patrick and Ley, Michael and Rabbidge, Emma and Schwarzkopf, Eric and Shrestha, Nitesh and Stojanovic, Nenad and Studer, Rudi and Stumme, Gerd and Walter, Bernd}, title = {Semantic Methods and Tools for Information Portals}, editor = {Dittrich, K. and König, W. and Oberweis, A. and Rannenberg, K. and Wahlster, W.}, booktitle = {INFORMATIK 2003 -- Innovative Informatikanwendungen (Band 1)}, series = {LNI}, publisher = {Gesellschaft für Informatik}, address = {Bonn}, year = {2003}, volume = {34}, pages = {116-131}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/agarwal2003semantic.pdf}, keywords = {2003, information, informationsportale, myown, ontologies, portals, semantic, semiport, web}, abstract = {The paper describes a set of approaches for representing and
cessing information within a semantically structured information
rtal, while offering the possibility to integrate own
formation. It discusses research performed within the project
emantic Methods and Tools for Information Portals (SemIPort)'.
particular, it focuses on (1) the development of scalable
oring, processing and querying methods for semantic data, (2)
sualization and browsing of complex data inventories, (3)
rsonalization and agent-based interaction, and (4) the
hancement of web mining approaches for use within a
mantics-based portal.} }

%0 = inproceedings %A = Agarwal, Sudhir and Fankhauser, Peter and Gonzalez-Ollala, Jorge and Hartmann, Jens and Hollfelder, Silvia and Jameson, Anthony and Klink, Stefan and Lehti, Patrick and Ley, Michael and Rabbidge, Emma and Schwarzkopf, Eric and Shrestha, Nitesh and Stojanovic, Nenad and Studer, Rudi and Stumme, Gerd and Walter, Bernd %B = INFORMATIK 2003 -- Innovative Informatikanwendungen (Band 1) %C = Bonn %D = 2003 %I = Gesellschaft für Informatik %T = Semantic Methods and Tools for Information Portals %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2003/agarwal2003semantic.pdf

Common text clustering techniques offer rather poor capabilities
r explaining to their users why a particular result has been
hieved. They have the disadvantage that they do not relate
mantically nearby terms and that they cannot explain how
sulting clusters are related to each other.
n this paper, we discuss a way of integrating a large thesaurus
nd the computation of lattices of resulting clusters into common text clustering
n order to overcome these two problems.
its major result, our approach achieves an explanation using an
propriate level of granularity at the concept level as well as
appropriate size and complexity of the explaining lattice of
sulting clusters.

@inproceedings{hotho03explaining, author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd}, title = {Explaining Text Clustering Results using Semantic Structures}, editor = {Lavrač, Nada and Gamberger, Dragan and Todorovski, Hendrik BlockeelLjupco}, booktitle = {Knowledge Discovery in Databases: PKDD 2003, 7th European Conference on Principles and Practice of Knowledge Discovery in Databases}, series = {LNAI}, publisher = {Springer}, address = {Heidelberg}, year = {2003}, volume = {2838}, pages = {217-228}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003explaining.pdf}, keywords = {2003, analysis, clustering, concept, fca, formal, myown, ontologies, semantic, semantics, text}, abstract = {Common text clustering techniques offer rather poor capabilities
r explaining to their users why a particular result has been
hieved. They have the disadvantage that they do not relate
mantically nearby terms and that they cannot explain how
sulting clusters are related to each other.
n this paper, we discuss a way of integrating a large thesaurus
nd the computation of lattices of resulting clusters into common text clustering
n order to overcome these two problems.
its major result, our approach achieves an explanation using an
propriate level of granularity at the concept level as well as
appropriate size and complexity of the explaining lattice of
sulting clusters.} }

%0 = inproceedings %A = Hotho, Andreas and Staab, Steffen and Stumme, Gerd %B = Knowledge Discovery in Databases: PKDD 2003, 7th European Conference on Principles and Practice of Knowledge Discovery in Databases %C = Heidelberg %D = 2003 %I = Springer %T = Explaining Text Clustering Results using Semantic Structures %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003explaining.pdf

Text document clustering plays an important role in providing intuitive
vigation and browsing mechanisms by organizing large amounts of information
to a small number of meaningful clusters. Standard partitional or agglomerative
ustering methods efficiently compute results to this end.
wever, the bag of words representation used for these clustering methods is often
satisfactory as it ignores relationships between important terms that do not
-occur literally. Also, it is mostly left to the user to find out why a particular partitioning
s been achieved, because it is only specified extensionally. In order to
al with the two problems, we integrate background knowledge into the process of
ustering text documents.
rst, we preprocess the texts, enriching their representations by background knowledge
ovided in a core ontology — in our application Wordnet. Then, we cluster
e documents by a partitional algorithm. Our experimental evaluation on Reuters
wsfeeds compares clustering results with pre-categorizations of news. In the experiments,
provements of results by background knowledge compared to the baseline
n be shown for many interesting tasks.
cond, the clustering partitions the large number of documents to a relatively small
mber of clusters, which may then be analyzed by conceptual clustering. In our approach,
applied Formal Concept Analysis. Conceptual clustering techniques are
own to be too slow for directly clustering several hundreds of documents, but they
ve an intensional account of cluster results. They allow for a concise description
commonalities and distinctions of different clusters. With background knowledge
ey even find abstractions like “food” (vs. specializations like “beef” or “corn”).
us, in our approach, partitional clustering reduces first the size of the problem
ch that it becomes tractable for conceptual clustering, which then facilitates the
derstanding of the results.

@techreport{hotho03textclustering, author = {Hotho, Andreas and Staab, Steffen and Stumme, Gerd}, title = {Text Clustering Based on Background Knowledge}, type = {Technical Report }, year = {2003}, volume = {425}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003text.pdf}, keywords = {2003, analysis, background, clustering, concept, fca, formal, knowledge, myown, ontologies, semantic, text, web}, abstract = {Text document clustering plays an important role in providing intuitive
vigation and browsing mechanisms by organizing large amounts of information
to a small number of meaningful clusters. Standard partitional or agglomerative
ustering methods efficiently compute results to this end.
wever, the bag of words representation used for these clustering methods is often
satisfactory as it ignores relationships between important terms that do not
-occur literally. Also, it is mostly left to the user to find out why a particular partitioning
s been achieved, because it is only specified extensionally. In order to
al with the two problems, we integrate background knowledge into the process of
ustering text documents.
rst, we preprocess the texts, enriching their representations by background knowledge
ovided in a core ontology — in our application Wordnet. Then, we cluster
e documents by a partitional algorithm. Our experimental evaluation on Reuters
wsfeeds compares clustering results with pre-categorizations of news. In the experiments,
provements of results by background knowledge compared to the baseline
n be shown for many interesting tasks.
cond, the clustering partitions the large number of documents to a relatively small
mber of clusters, which may then be analyzed by conceptual clustering. In our approach,
applied Formal Concept Analysis. Conceptual clustering techniques are
own to be too slow for directly clustering several hundreds of documents, but they
ve an intensional account of cluster results. They allow for a concise description
commonalities and distinctions of different clusters. With background knowledge
ey even find abstractions like “food” (vs. specializations like “beef” or “corn”).
us, in our approach, partitional clustering reduces first the size of the problem
ch that it becomes tractable for conceptual clustering, which then facilitates the
derstanding of the results.} }

%0 = techreport %A = Hotho, Andreas and Staab, Steffen and Stumme, Gerd %D = 2003 %T = Text Clustering Based on Background Knowledge %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2003/hotho2003text.pdf

@inproceedings{studer03building, author = {Studer, Rudi and Stumme, Gerd and Handschuh, Siegfried and Hotho, Andreas and Motik, B.}, title = {Building and Using the Semantic Web}, booktitle = {New Trends in Knowledge Processing -- Data Mining, Semantic Web and Computational}, address = {Osaka, Japan}, year = {2003}, pages = {31-34}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/Sanken03.pdf}, keywords = {2003, data, kdd, mining, myown, ontologies, semantic, web} }

%0 = inproceedings %A = Studer, Rudi and Stumme, Gerd and Handschuh, Siegfried and Hotho, Andreas and Motik, B. %B = New Trends in Knowledge Processing -- Data Mining, Semantic Web and Computational %C = Osaka, Japan %D = 2003 %T = Building and Using the Semantic Web %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2003/Sanken03.pdf

@proceedings{berendt02semantic,, title = {Semantic Web Mining. Proc. of the Semantic Web Mining Workshop of the 13th Europ. Conf. on
Machine Learning (ECML'02) / 6th Europ. Conf. on Principles and
Practice of Knowledge Discovery in Databases (PKDD'02)}, editor = {Berendt, B. and Hotho, A. and Stumme, G.}, address = {Helsinki, Finland}, year = {2002}, url = {http://km.aifb.uni-karlsruhe.de/ws/semwebmine2002/online_html}, keywords = {2002, ecml, mining, myown, pkdd, proceedings, semantic, web, workshop} }

%0 = proceedings %C = Helsinki, Finland %D = 2002 %T = Semantic Web Mining. Proc. of the Semantic Web Mining Workshop of the 13th Europ. Conf. on
Machine Learning (ECML'02) / 6th Europ. Conf. on Principles and
Practice of Knowledge Discovery in Databases (PKDD'02) %U = http://km.aifb.uni-karlsruhe.de/ws/semwebmine2002/online_html

@inproceedings{berendt02towards, author = {Berendt, B. and Hotho, A. and Stumme, G.}, title = {Towards Semantic Web Mining}, editor = {Horrocks, I. and Hendler, J.}, booktitle = {The Semantic Web -- ISWC 2002}, series = {LNCS}, publisher = {Springer}, address = {Heidelberg}, year = {2002}, pages = {264-278}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/ISWC02.pdf}, keywords = {2002, mining, myown, semantic, web} }

%0 = inproceedings %A = Berendt, B. and Hotho, A. and Stumme, G. %B = The Semantic Web -- ISWC 2002 %C = Heidelberg %D = 2002 %I = Springer %T = Towards Semantic Web Mining %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2002/ISWC02.pdf

@inproceedings{bozsak2002towards, author = {Bozsak, E. and Ehrig, Marc and Handschuh, Siegfried and Hotho, Andreas and Maedche, Alexander and Motik, Boris and Oberle, Daniel and Schmitz, Christoph and Staab, Steffen and Stojanovic, Ljiljana and Stojanovic, Nenad and Studer, Rudi and Stumme, Gerd and Sure, York and Tane, Julien and Volz, Raphael and Zacharias, Valentin}, title = {KAON - Towards a large scale Semantic Web}, editor = {Bauknecht, Kurt and Tjoa, A. Min and Quirchmayr, Gerald}, booktitle = {Proceedings of the Third International Conference on E-Commerce and Web Technologies (EC-Web 2002), Aix-en-Provence, France}, series = {LNCS}, publisher = {Springer}, year = {2002}, volume = {2455}, pages = {304-313}, url = {http://www.aifb.uni-karlsruhe.de/WBS/ysu/publications/2002_ecweb_kaon.pdf}, keywords = {2002, aifb, kaon, karlsruhe, l3s, myown, ontologies, semantic, social, web} }

%0 = inproceedings %A = Bozsak, E. and Ehrig, Marc and Handschuh, Siegfried and Hotho, Andreas and Maedche, Alexander and Motik, Boris and Oberle, Daniel and Schmitz, Christoph and Staab, Steffen and Stojanovic, Ljiljana and Stojanovic, Nenad and Studer, Rudi and Stumme, Gerd and Sure, York and Tane, Julien and Volz, Raphael and Zacharias, Valentin %B = Proceedings of the Third International Conference on E-Commerce and Web Technologies (EC-Web 2002), Aix-en-Provence, France %D = 2002 %I = Springer %T = KAON - Towards a large scale Semantic Web %U = http://www.aifb.uni-karlsruhe.de/WBS/ysu/publications/2002_ecweb_kaon.pdf

@inproceedings{gonzalez02semantic, author = {Gonzalez-Olalla, J. and Stumme, G.}, title = {Semantic Methods and Tools for Information Portals - The SemIPort Project (Project Description)}, editor = {Berendt, B. and Hotho, A. and Stumme, G.}, booktitle = {Semantic Web Mining. Proc. of the Semantic Web Mining Workshop of the 13th Europ. Conf.}, address = {Helsinki}, year = {2002}, pages = {90}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/gonzalez2002semantic.pdf}, keywords = {2002, Semantic, bmbf, information, informationsportale, myown, ontologies, portal, portals, project, semantic, semiport, web} }

%0 = inproceedings %A = Gonzalez-Olalla, J. and Stumme, G. %B = Semantic Web Mining. Proc. of the Semantic Web Mining Workshop of the 13th Europ. Conf. %C = Helsinki %D = 2002 %T = Semantic Methods and Tools for Information Portals - The SemIPort Project (Project Description) %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2002/gonzalez2002semantic.pdf

@inproceedings{hartmann02semanticweb, author = {Hartmann, J. and Hotho, A. and Stumme, G.}, title = {Semantic Web Mining for Building Information Portals (Position Paper)}, booktitle = {Proc. Arbeitskreistreffen Knowledge Discovery}, address = {Oldenburg}, year = {2002}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/hartmann2002semanticweb.pdf}, keywords = {2002, bmbf, information, informationsportale, myown, ontologies, portal, portals, project, projekt, semantic, semiport, web} }

%0 = inproceedings %A = Hartmann, J. and Hotho, A. and Stumme, G. %B = Proc. Arbeitskreistreffen Knowledge Discovery %C = Oldenburg %D = 2002 %T = Semantic Web Mining for Building Information Portals (Position Paper) %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2002/hartmann2002semanticweb.pdf

@inproceedings{schmitz02accessing, author = {Schmitz, C. and Staab, S. and Studer, R. and Stumme, G. and Tane, J.}, title = {Accessing Distributed Learning Repositories through a Courseware
Watchdog}, editor = {Driscoll, M. and Reeves, T.C.}, booktitle = {Proc. of E-Learning 2002 World Conference on E-Learning in Corporate, Government, Healthcare and Higher Education on (E-Learning 2002)}, address = {Norfolk}, year = {2002}, volume = {AACE}, pages = {909-915}, note = {Awarded paper}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/E-Learn02.pdf}, keywords = {2002, FCA, OntologyHandbook, courseware, crawler, edutella, fca, myown, ontologies, p2p, semantic, watchdog, web} }

%0 = inproceedings %A = Schmitz, C. and Staab, S. and Studer, R. and Stumme, G. and Tane, J. %B = Proc. of E-Learning 2002 World Conference on E-Learning in Corporate, Government, Healthcare and Higher Education on (E-Learning 2002) %C = Norfolk %D = 2002 %T = Accessing Distributed Learning Repositories through a Courseware
Watchdog %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2002/E-Learn02.pdf

@inproceedings{stumme02usage, author = {Stumme, G. and Berendt, B. and Hotho, A.}, title = {Usage Mining for and on the Semantic Web}, booktitle = {Proc. NSF Workshop on Next Generation Data Mining}, address = {Baltimore}, year = {2002}, pages = {77-86}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/NSF-NGDM02.pdf}, keywords = {2002, mining, myown, semantic, usage, web} }

%0 = inproceedings %A = Stumme, G. and Berendt, B. and Hotho, A. %B = Proc. NSF Workshop on Next Generation Data Mining %C = Baltimore %D = 2002 %T = Usage Mining for and on the Semantic Web %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2002/NSF-NGDM02.pdf

@incollection{stumme02using, author = {Stumme, G.}, title = {Using Ontologies and Formal Concept Analysis for Organizing Business Knowledge}, editor = {Becker, J. and Knackstedt, R.}, booktitle = {Wissensmanagement mit Referenzmodellen -- Konzepte für die Anwendungssystem- und Organisationsgestaltung}, publisher = {Physica}, address = {Heidelberg}, year = {2002}, pages = {163-174}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2001/REFMOD01.ps}, keywords = {2002, analysis, business, concept, fca, formal, knowledge, management, myown, ontologies, semantic, web, wissensmanagement} }

%0 = incollection %A = Stumme, G. %B = Wissensmanagement mit Referenzmodellen -- Konzepte für die Anwendungssystem- und Organisationsgestaltung %C = Heidelberg %D = 2002 %I = Physica %T = Using Ontologies and Formal Concept Analysis for Organizing Business Knowledge %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2001/REFMOD01.ps

Distributional information has recently been implicated as playing an important role in several aspects of language ability. Learning the meaning of a word is thought to be dependent, at least in part, on exposure to the word in its linguistic contexts of use. In two experiments, we manipulated subjects ’ contextual experience with marginally familiar and nonce words. Results showed that similarity judgements involving these words were affected by the distributional properties of the contexts in which they were read. The accrual of contextual experience was simulated in a semantic space model, by successively adding larger amounts of experience in the form of item-in-context exemplars sampled from the British National Corpus. The experiments and the simulation

@inproceedings{Mcdonald01testingthe, author = {Mcdonald, Scott and Ramscar, Michael}, title = {Testing the distributional hypothesis: The influence of context on judgements of semantic similarity}, booktitle = {In Proceedings of the 23rd Annual Conference of the Cognitive Science Society}, year = {2001}, pages = {611--6}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.7535}, keywords = {distance, distributional, hypothesis, measure, semantic, similarity, tagging}, abstract = {Distributional information has recently been implicated as playing an important role in several aspects of language ability. Learning the meaning of a word is thought to be dependent, at least in part, on exposure to the word in its linguistic contexts of use. In two experiments, we manipulated subjects ’ contextual experience with marginally familiar and nonce words. Results showed that similarity judgements involving these words were affected by the distributional properties of the contexts in which they were read. The accrual of contextual experience was simulated in a semantic space model, by successively adding larger amounts of experience in the form of item-in-context exemplars sampled from the British National Corpus. The experiments and the simulation} }

%0 = inproceedings %A = Mcdonald, Scott and Ramscar, Michael %B = In Proceedings of the 23rd Annual Conference of the Cognitive Science Society %D = 2001 %T = Testing the distributional hypothesis: The influence of context on judgements of semantic similarity %U = http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.7535

@inproceedings{stumme01bottom, author = {Stumme, G. and Maedche, A.}, title = {FCA-Merge: Bottom-Up Merging of Ontologies.}, editor = {Nebel, B.}, booktitle = {Proc. 17th Intl. Conf. on Artificial Intelligence (IJCAI '01)}, address = {Seattle, WA, USA}, year = {2001}, pages = {225-230}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2001/IJCAI01.pdf}, keywords = {2001, analysis, concept, fca, formal, merging, myown, ontologies, ontology, semantic, web} }

%0 = inproceedings %A = Stumme, G. and Maedche, A. %B = Proc. 17th Intl. Conf. on Artificial Intelligence (IJCAI '01) %C = Seattle, WA, USA %D = 2001 %T = FCA-Merge: Bottom-Up Merging of Ontologies. %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2001/IJCAI01.pdf

@proceedings{stumme01semantic,, title = {Semantic Web Mining. Workshop Proceedings.}, editor = {Stumme, G. and Hotho, A. and Berendt, B.}, address = {Freiburg}, year = {2001}, url = {http://semwebmine2001.aifb.uni-karlsruhe.de/online.html}, keywords = {2001, ecml, kdd, mining, myown, pkdd, proceedings, semantic, web, workshop} }

%0 = proceedings %C = Freiburg %D = 2001 %T = Semantic Web Mining. Workshop Proceedings. %U = http://semwebmine2001.aifb.uni-karlsruhe.de/online.html

@inproceedings{stumme00towardsanorder, author = {Stumme, G. and Studer, R. and Sure, Y.}, title = {Towards an Order-Theoretical Foundation for Maintaining and Merging Ontologies}, editor = {Bodendorf, F. and Grauer, M.}, booktitle = {Verbundtagung Wirtschaftsinformatik 2000}, publisher = {Shaker}, address = {Aachen}, year = {2000}, pages = {136-149}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2000/REFMOD00.pdf}, keywords = {2000, analysis, concept, fca, formal, merging, myown, ontologies, ontology, semantic, web} }

%0 = inproceedings %A = Stumme, G. and Studer, R. and Sure, Y. %B = Verbundtagung Wirtschaftsinformatik 2000 %C = Aachen %D = 2000 %I = Shaker %T = Towards an Order-Theoretical Foundation for Maintaining and Merging Ontologies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2000/REFMOD00.pdf

@misc{hirst97lexical, author = {Hirst, G. and St-Onge, D.}, title = {Lexical Chains as representation of context for the detection and correction
malapropisms}, year = {1997}, url = {citeseer.ist.psu.edu/hirst97lexical.html}, keywords = {hirst, lexical, relatedness, semantic, similarity} }

%0 = misc %A = Hirst, G. and St-Onge, D. %D = 1997 %T = Lexical Chains as representation of context for the detection and correction
malapropisms %U = citeseer.ist.psu.edu/hirst97lexical.html

@inproceedings{Resnik95, author = {Resnik, Philip}, title = {Using Information Content to Evaluate Semantic Similarity in a Taxonomy}, booktitle = {Proceedings of the XI International Joint Conferences on Artificial}, year = {1995}, pages = {448-453}, keywords = {information, measure, semantic, similarity, taxonomy} }

%0 = inproceedings %A = Resnik, Philip %B = Proceedings of the XI International Joint Conferences on Artificial %D = 1995 %T = Using Information Content to Evaluate Semantic Similarity in a Taxonomy

@book{harris68mathematical, author = {Harris, Z. S.}, title = {Mathematical Structures of Language}, publisher = {Wiley}, address = {New York}, year = {1968}, keywords = {distributional, hypothesis, measure, measures, semantic, similarity} }

%0 = book %A = Harris, Z. S. %C = New York %D = 1968 %I = Wiley %T = Mathematical Structures of Language