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{cattuto2008semantic, 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}, pages = {39--43}, note = {ISBN 978-960-89282-6-8}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantic.pdf}, isbn = {978-960-89282-6-8}, keywords = {2008, ol_web2.0, itegpub, tagorapub, methods_concepts, olp3, methods_concepthierarchy, myown, semantic_relatedness, tag_relatedness}, 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://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantic.pdf

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{cattuto2008semantic, 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}, pages = {39--43}, note = {ISBN 978-960-89282-6-8}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantic.pdf}, isbn = {978-960-89282-6-8}, keywords = {2008, ol_web2.0, itegpub, tagorapub, methods_concepts, olp3, methods_concepthierarchy, myown, semantic_relatedness, tag_relatedness}, 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://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantic.pdf

Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For taskslike 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{cattuto2008semantica, 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://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf}, doi = {http://dx.doi.org/10.1007/978-3-540-88564-1_39}, keywords = {2008, ol_web2.0, tagging, similarity, tag, methods_concepts, semantic, methods_concepthierarchy, myown, grounding, iswc2008, itegpub, relatedness, tagorapub, sw, semantic_relatedness}, abstract = {Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For taskslike 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://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf

Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For taskslike 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{cattuto2008semantica, 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://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf}, doi = {http://dx.doi.org/10.1007/978-3-540-88564-1_39}, keywords = {2008, ol_web2.0, tagging, similarity, tag, methods_concepts, semantic, methods_concepthierarchy, myown, grounding, iswc2008, itegpub, relatedness, tagorapub, sw, semantic_relatedness}, abstract = {Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For taskslike 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://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf

The emergence of collaborative tagging systems with their underlying flat and uncontrolled resource organization paradigm has led to a large number of research activities focussing on a formal description and analysis of the resulting “folksonomies??. An interesting outcome is that the characteristic qualities of these systems seem to be inverse to more traditional knowledge structuring approaches like taxonomies or ontologies: The latter provide rich and precise semantics, but suffer - amongst others - from a knowledge acquisition bottleneck. An important step towards exploiting the possible synergies by bridging the gap between both paradigms is the automatic extraction of relations between tags in a folksonomy. This position paper presents preliminary results of ongoing work to induce hierarchical relationships among tags by analyzing the aggregated data of collaborative tagging systems as a basis for an ontology learning procedure.

@inproceedings{benz2007position, author = {Benz, Dominik and Hotho, Andreas}, title = {Position Paper: Ontology Learning from Folksonomies}, editor = {Hinneburg, Alexander}, booktitle = {Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007)}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, year = {2007}, pages = {109--112}, note = {http://lwa07.informatik.uni-halle.de/kdml07/kdml07.htm}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2007position.pdf}, isbn = {978-3-86010-907-6}, keywords = {2007, ol_web2.0, itegpub, tagorapub, rel2, ibm-kde-tagging, methods_concepthierarchy, diploma_thesis, ontology_learning, rel1, myown}, abstract = {The emergence of collaborative tagging systems with their underlying flat and uncontrolled resource organization paradigm has led to a large number of research activities focussing on a formal description and analysis of the resulting “folksonomies??. An interesting outcome is that the characteristic qualities of these systems seem to be inverse to more traditional knowledge structuring approaches like taxonomies or ontologies: The latter provide rich and precise semantics, but suffer - amongst others - from a knowledge acquisition bottleneck. An important step towards exploiting the possible synergies by bridging the gap between both paradigms is the automatic extraction of relations between tags in a folksonomy. This position paper presents preliminary results of ongoing work to induce hierarchical relationships among tags by analyzing the aggregated data of collaborative tagging systems as a basis for an ontology learning procedure.} }

%0 = inproceedings %A = Benz, Dominik and Hotho, Andreas %B = Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007) %D = 2007 %I = Martin-Luther-Universität Halle-Wittenberg %T = Position Paper: Ontology Learning from Folksonomies %U = http://www.kde.cs.uni-kassel.de/pub/pdf/benz2007position.pdf

The emergence of collaborative tagging systems with their underlying flat and uncontrolled resource organization paradigm has led to a large number of research activities focussing on a formal description and analysis of the resulting “folksonomies�?. An interesting outcome is that the characteristic qualities of these systems seem to be inverse to more traditional knowledge structuring approaches like taxonomies or ontologies: The latter provide rich and precise semantics, but suffer - amongst others - from a knowledge acquisition bottleneck. An important step towards exploiting the possible synergies by bridging the gap between both paradigms is the automatic extraction of relations between tags in a folksonomy. This position paper presents preliminary results of ongoing work to induce hierarchical relationships among tags by analyzing the aggregated data of collaborative tagging systems as a basis for an ontology learning procedure.

@inproceedings{benz2007position, author = {Benz, Dominik and Hotho, Andreas}, title = {Position Paper: Ontology Learning from Folksonomies}, editor = {Hinneburg, Alexander}, booktitle = {Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007)}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, year = {2007}, pages = {109--112}, note = {http://lwa07.informatik.uni-halle.de/kdml07/kdml07.htm}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2007position.pdf}, isbn = {978-3-86010-907-6}, keywords = {2007, ol_web2.0, itegpub, tagorapub, rel2, ibm-kde-tagging, methods_concepthierarchy, diploma_thesis, ontology_learning, rel1, myown}, abstract = {The emergence of collaborative tagging systems with their underlying flat and uncontrolled resource organization paradigm has led to a large number of research activities focussing on a formal description and analysis of the resulting “folksonomies�?. An interesting outcome is that the characteristic qualities of these systems seem to be inverse to more traditional knowledge structuring approaches like taxonomies or ontologies: The latter provide rich and precise semantics, but suffer - amongst others - from a knowledge acquisition bottleneck. An important step towards exploiting the possible synergies by bridging the gap between both paradigms is the automatic extraction of relations between tags in a folksonomy. This position paper presents preliminary results of ongoing work to induce hierarchical relationships among tags by analyzing the aggregated data of collaborative tagging systems as a basis for an ontology learning procedure.} }

%0 = inproceedings %A = Benz, Dominik and Hotho, Andreas %B = Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007) %D = 2007 %I = Martin-Luther-Universität Halle-Wittenberg %T = Position Paper: Ontology Learning from Folksonomies %U = http://www.kde.cs.uni-kassel.de/pub/pdf/benz2007position.pdf