@incollection{tagging-cattuto,
  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.}},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {The Semantic Web - ISWC 2008},
  citeulike-article-id = {4718854},
  citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-540-88564-1\_39},
  citeulike-linkout-1 = {http://www.springerlink.com/content/9044260283881v78},
  doi = {10.1007/978-3-540-88564-1\_39},
  editor = {Sheth, Amit and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy and Thirunarayan, Krishnaprasad},
  interhash = {b44538648cfd476d6c94e30bc6626c86},
  intrahash = {022ccb7184fcd0e43092fca13fd56a00},
  journal = {The Semantic Web - ISWC 2008},
  pages = {615--631},
  posted-at = {2011-09-09 20:06:23},
  priority = {2},
  publisher = {Springer Berlin / Heidelberg},
  series = {Lecture Notes in Computer Science},
  title = {{Semantic Grounding of Tag Relatedness in Social Bookmarking Systems}},
  url = {http://tagora-project.eu/wp-content/2009/09/cattuto_iswc2008.pdf},
  volume = 5318,
  year = 2008
}

@inproceedings{cattuto2008semantic,
  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.},
  address = {Patras, Greece},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proceedings of the 3rd Workshop on Ontology Learning and Population (OLP3)},
  file = {cattuto2008semantic.pdf:cattuto2008semantic.pdf:PDF},
  groups = {public},
  homepage = {http://olp.dfki.de/olp3/},
  interhash = {cc62b733f6e0402db966d6dbf1b7711f},
  intrahash = {3b0aca61b24e4343bd80390614e3066e},
  isbn = {978-960-89282-6-8},
  month = {July},
  note = {ISBN 978-960-89282-6-8},
  pages = {39--43},
  title = {Semantic Analysis of Tag Similarity Measures in Collaborative Tagging Systems},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantic.pdf},
  username = {dbenz},
  year = 2008
}

@inproceedings{cattuto2008semantica,
  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.},
  address = {Heidelberg},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {The Semantic Web -- ISWC 2008, Proc.Intl. Semantic Web Conference 2008},
  doi = {http://dx.doi.org/10.1007/978-3-540-88564-1_39},
  editor = {Sheth, Amit P. and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy W. and Thirunarayan, Krishnaprasad},
  file = {cattuto2008semantica.pdf:cattuto2008semantica.pdf:PDF},
  groups = {public},
  interhash = {b44538648cfd476d6c94e30bc6626c86},
  intrahash = {27198c985b3bdb6daab0f7e961b370a9},
  pages = {615--631},
  publisher = {Springer},
  series = {LNAI},
  title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf},
  username = {dbenz},
  volume = 5318,
  year = 2008
}

@inproceedings{bade2008evaluation,
  abstract = {Several learning tasks comprise hierarchies. Comparison with a "goldstandard" is often performed to evaluate the quality of a learned hierarchy. We assembled various similarity metrics that have been proposed in different disciplines and compared them in a unified interdisciplinary framework for hierarchical evaluation which is based on the distinction of three fundamental dimensions. Identifying deficiencies for measuring structural similarity, we suggest three new measures for this purpose, either extending existing ones or based on new ideas. Experiments with an artificial dataset were performed to compare the different measures. As shown by our results, the measures vary greatly in their properties.},
  address = {Berlin-Heidelberg},
  author = {Bade, Korinna and Benz, Dominik},
  booktitle = {Proceedings of the 32nd Annual Conference of the German Classification Society - Advances in Data Analysis, Data Handling and Business Intelligence (GfKl 2008)},
  file = {bade2008evaluation.pdf:bade2008evaluation.pdf:PDF},
  groups = {public},
  interhash = {8bb09e3197d01f7c23481c2cd68533af},
  intrahash = {ec033805bc90ab87c99860e29f0d00dd},
  note = {in press},
  publisher = {Springer},
  series = {Studies in Classification, Data Analysis, and Knowledge Organization},
  title = {Evaluation Strategies for Learning Algorithms of Hierarchical Structures},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/bade2008evaluation.pdf},
  username = {dbenz},
  year = 2008
}

@inproceedings{benz2008analyzing,
  abstract = {The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance.},
  author = {Benz, Dominik and Grobelnik, Marko and Hotho, Andreas and Jäschke, Robert and Mladenic, Dunja and Servedio, Vito D. P. and Sizov, Sergej and Szomszor, Martin},
  booktitle = {Proceedings of the Dagstuhl Seminar on Social Web Communities},
  editor = {Alani, Harith and Staab, Steffen and Stumme, Gerd},
  file = {benz2008analyzing.pdf:benz2008analyzing.pdf:PDF},
  groups = {public},
  interhash = {d738d9d90c1c466ee0a73ac0cc3dc4c1},
  intrahash = {6918e578527dec96abb5718f105d9f78},
  issn = {1862-4405},
  number = 08391,
  title = {Analyzing Tag Semantics Across Collaborative Tagging Systems},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2008analyzing.pdf},
  username = {dbenz},
  year = 2008
}

@inproceedings{cattuto2008semantic,
  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. 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.},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {The Semantic Web - ISWC 2008},
  doi = {10.1007/978-3-540-88564-1_39},
  interhash = {b44538648cfd476d6c94e30bc6626c86},
  intrahash = {4752f261d03cead0c52565148a0ba1c9},
  isbn = {978-3-540-88563-4},
  pages = {615--631},
  publisher = {Springer Berlin / Heidelberg},
  series = {Lecture Notes in Computer Science},
  title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf},
  volume = 5318,
  year = 2008
}

@inproceedings{bade2008evaluation,
  abstract = {Several learning tasks comprise hierarchies. Comparison with a "goldstandard" is often performed to evaluate the quality of a learned hierarchy. We assembled various similarity metrics that have been proposed in different disciplines and compared them in a unified interdisciplinary framework for hierarchical evaluation which is based on the distinction of three fundamental dimensions. Identifying deficiencies for measuring structural similarity, we suggest three new measures for this purpose, either extending existing ones or based on new ideas. Experiments with an artificial dataset were performed to compare the different measures. As shown by our results, the measures vary greatly in their properties.},
  address = {Berlin-Heidelberg},
  author = {Bade, Korinna and Benz, Dominik},
  booktitle = {Proceedings of the 32nd Annual Conference of the German Classification Society - Advances in Data Analysis, Data Handling and Business Intelligence (GfKl 2008)},
  file = {bade2008evaluation.pdf:bade2008evaluation.pdf:PDF},
  groups = {public},
  interhash = {8bb09e3197d01f7c23481c2cd68533af},
  intrahash = {ec033805bc90ab87c99860e29f0d00dd},
  note = {in press},
  publisher = {Springer},
  series = {Studies in Classification, Data Analysis, and Knowledge Organization},
  timestamp = {2008-12-19 09:18:13},
  title = {Evaluation Strategies for Learning Algorithms of Hierarchical Structures},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/bade2008evaluation.pdf},
  username = {dbenz},
  year = 2008
}

@inproceedings{benz2008analyzing,
  abstract = {The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance.},
  author = {Benz, Dominik and Grobelnik, Marko and Hotho, Andreas and Jäschke, Robert and Mladenic, Dunja and Servedio, Vito D. P. and Sizov, Sergej and Szomszor, Martin},
  booktitle = {Proceedings of the Dagstuhl Seminar on Social Web Communities},
  editor = {Alani, Harith and Staab, Steffen and Stumme, Gerd},
  file = {benz2008analyzing.pdf:benz2008analyzing.pdf:PDF},
  groups = {public},
  interhash = {d738d9d90c1c466ee0a73ac0cc3dc4c1},
  intrahash = {6918e578527dec96abb5718f105d9f78},
  issn = {1862-4405},
  number = 08391,
  timestamp = {2009-10-01 18:35:30},
  title = {Analyzing Tag Semantics Across Collaborative Tagging Systems},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2008analyzing.pdf},
  username = {dbenz},
  year = 2008
}

@inproceedings{cattuto2008semantica,
  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.},
  address = {Heidelberg},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {The Semantic Web -- ISWC 2008, Proc.Intl. Semantic Web Conference 2008},
  doi = {http://dx.doi.org/10.1007/978-3-540-88564-1_39},
  editor = {Sheth, Amit P. and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy W. and Thirunarayan, Krishnaprasad},
  file = {cattuto2008semantica.pdf:cattuto2008semantica.pdf:PDF},
  groups = {public},
  interhash = {b44538648cfd476d6c94e30bc6626c86},
  intrahash = {27198c985b3bdb6daab0f7e961b370a9},
  pages = {615--631},
  publisher = {Springer},
  series = {LNAI},
  timestamp = {2009-09-14 19:12:46},
  title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf},
  username = {dbenz},
  volume = 5318,
  year = 2008
}

@inproceedings{cattuto2008semantic,
  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.},
  address = {Patras, Greece},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proceedings of the 3rd Workshop on Ontology Learning and Population (OLP3)},
  file = {cattuto2008semantic.pdf:cattuto2008semantic.pdf:PDF},
  groups = {public},
  homepage = {http://olp.dfki.de/olp3/},
  interhash = {cc62b733f6e0402db966d6dbf1b7711f},
  intrahash = {3b0aca61b24e4343bd80390614e3066e},
  isbn = {978-960-89282-6-8},
  month = {July},
  note = {ISBN 978-960-89282-6-8},
  pages = {39--43},
  timestamp = {2009-09-14 19:31:25},
  title = {Semantic Analysis of Tag Similarity Measures in Collaborative Tagging Systems},
  url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantic.pdf},
  username = {dbenz},
  year = 2008
}

@inproceedings{cattuto2008semantic,
  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. 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.},
  address = {Heidelberg},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {The Semantic Web -- ISWC 2008, Proc.Intl. Semantic Web Conference 2008},
  editor = {Sheth, Amit P. and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy W. and Thirunarayan, Krishnaprasad},
  interhash = {b44538648cfd476d6c94e30bc6626c86},
  intrahash = {27198c985b3bdb6daab0f7e961b370a9},
  pages = {615--631},
  publisher = {Springer},
  series = {LNAI},
  title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems},
  url = {http://dx.doi.org/10.1007/978-3-540-88564-1_39},
  volume = 5318,
  year = 2008
}

@inproceedings{cattuto08-semantic,
  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.},
  address = {Patras, Greece},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proceedings of the 3rd Workshop on Ontology Learning and Population (OLP3)},
  interhash = {cc62b733f6e0402db966d6dbf1b7711f},
  intrahash = {3b0aca61b24e4343bd80390614e3066e},
  month = {July},
  title = {Semantic Analysis of Tag Similarity Measures in Collaborative Tagging Systems},
  url = {http://olp.dfki.de/olp3/},
  year = 2008
}

@inproceedings{benz2008analyzing,
  abstract = {The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance. },
  address = {Dagstuhl, Germany},
  author = {Benz, Dominik and Grobelnik, Marko and Hotho, Andreas and Jäschke, Robert and Mladenic, Dunja and Servedio, Vito D. P. and Sizov, Sergej and Szomszor, Martin},
  booktitle = {Social Web Communities},
  editor = {Alani, Harith and Staab, Steffen and Stumme, Gerd},
  interhash = {d738d9d90c1c466ee0a73ac0cc3dc4c1},
  intrahash = {7ab57438aa5a68137e46dab8dadd4b2c},
  issn = {1862-4405},
  number = 08391,
  publisher = {Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik},
  series = {Dagstuhl Seminar Proceedings},
  title = {Analyzing Tag Semantics Across Collaborative Tagging Systems},
  url = {http://drops.dagstuhl.de/opus/volltexte/2008/1785},
  year = 2008
}

@inproceedings{benz2008analyzing,
  abstract = {The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance. },
  address = {Dagstuhl, Germany},
  author = {Benz, Dominik and Grobelnik, Marko and Hotho, Andreas and Jäschke, Robert and Mladenic, Dunja and Servedio, Vito D. P. and Sizov, Sergej and Szomszor, Martin},
  booktitle = {Social Web Communities},
  editor = {Alani, Harith and Staab, Steffen and Stumme, Gerd},
  interhash = {d738d9d90c1c466ee0a73ac0cc3dc4c1},
  intrahash = {7ab57438aa5a68137e46dab8dadd4b2c},
  issn = {1862-4405},
  month = sep,
  number = 08391,
  publisher = {Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik},
  series = {Dagstuhl Seminar Proceedings},
  title = {Analyzing Tag Semantics Across Collaborative Tagging Systems},
  url = {http://drops.dagstuhl.de/opus/volltexte/2008/1785},
  year = 2008
}

@inproceedings{cattuto2008semantic,
  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.},
  address = {Patras, Greece},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proceedings of the 3rd Workshop on Ontology Learning and Population (OLP3)},
  interhash = {cc62b733f6e0402db966d6dbf1b7711f},
  intrahash = {3b0aca61b24e4343bd80390614e3066e},
  isbn = {978-960-89282-6-8},
  month = jul,
  pages = {39--43},
  title = {Semantic Analysis of Tag Similarity Measures in Collaborative Tagging Systems},
  url = {http://olp.dfki.de/olp3/},
  year = 2008
}

@misc{cattuto-2008,
  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.},
  author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  interhash = {cc62b733f6e0402db966d6dbf1b7711f},
  intrahash = {78fd64c3db55e6387ebdeb6c40054542},
  title = {Semantic Analysis of Tag Similarity Measures in Collaborative Tagging   Systems},
  url = {http://www.citebase.org/abstract?id=oai:arXiv.org:0805.2045},
  year = 2008
}