Recent research has demonstrated how the widespread adoption of collaborative tagging systems yields emergent semantics. In recent years, much has been learned about how to harvest the data produced by taggers for engineering light-weight ontologies. For example, existing measures of tag similarity and tag relatedness have proven crucial step stones for making latent semantic relations in tagging systems explicit. However, little progress has been made on other issues, such as understanding the different levels of tag generality (or tag abstractness), which is essential for, among others, identifying hierarchical relationships between concepts. In this paper we aim to address this gap. Starting from a review of linguistic definitions of word abstractness, we first use several large-scale ontologies and taxonomies as grounded measures of word generality, including Yago, Wordnet, DMOZ and Wikitaxonomy. Then, we introduce and apply several folksonomy-based methods to measure the level of generality of given tags. We evaluate these methods by comparing them with the grounded measures. Our results suggest that the generality of tags in social tagging systems can be approximated with simple measures. Our work has implications for a number of problems related to social tagging systems, including search, tag recommendation, and the acquisition of light-weight ontologies from tagging data.

@inproceedings{benz2011measuring, author = {Benz, Dominik and Körner, Christian and Hotho, Andreas and Stumme, Gerd and Strohmaier, Markus}, title = {One Tag to Bind Them All : Measuring Term Abstractness in Social Metadata}, editor = {Antoniou, Grigoris and Grobelnik, Marko and Simperl, Elena and Parsia, Bijan and Plexousakis, Dimitris and Pan, Jeff and Leenheer, Pieter De}, booktitle = {Proceedings of the 8th Extended Semantic Web Conference (ESWC 2011)}, address = {Heraklion, Crete}, year = {2011}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2011measuring.pdf}, keywords = {2011, abstractness, itegpub, l3s, myown, seminar, summer, tagging}, abstract = {Recent research has demonstrated how the widespread adoption of collaborative tagging systems yields emergent semantics. In recent years, much has been learned about how to harvest the data produced by taggers for engineering light-weight ontologies. For example, existing measures of tag similarity and tag relatedness have proven crucial step stones for making latent semantic relations in tagging systems explicit. However, little progress has been made on other issues, such as understanding the different levels of tag generality (or tag abstractness), which is essential for, among others, identifying hierarchical relationships between concepts. In this paper we aim to address this gap. Starting from a review of linguistic definitions of word abstractness, we first use several large-scale ontologies and taxonomies as grounded measures of word generality, including Yago, Wordnet, DMOZ and Wikitaxonomy. Then, we introduce and apply several folksonomy-based methods to measure the level of generality of given tags. We evaluate these methods by comparing them with the grounded measures. Our results suggest that the generality of tags in social tagging systems can be approximated with simple measures. Our work has implications for a number of problems related to social tagging systems, including search, tag recommendation, and the acquisition of light-weight ontologies from tagging data.} }

%0 = inproceedings %A = Benz, Dominik and Körner, Christian and Hotho, Andreas and Stumme, Gerd and Strohmaier, Markus %B = Proceedings of the 8th Extended Semantic Web Conference (ESWC 2011) %C = Heraklion, Crete %D = 2011 %T = One Tag to Bind Them All : Measuring Term Abstractness in Social Metadata %U = http://www.kde.cs.uni-kassel.de/pub/pdf/benz2011measuring.pdf

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

The annotation of web sites in social bookmarking systemshas become a popular way to manage and find informationon the web. The community structure of such systems attractsspammers: recent post pages, popular pages or specifictag pages can be manipulated easily. As a result, searchingor tracking recent posts does not deliver quality resultsannotated in the community, but rather unsolicited, oftencommercial, web sites. To retain the benefits of sharingone’s web content, spam-fighting mechanisms that can facethe flexible strategies of spammers need to be developed.

@inproceedings{krause2008antisocial, author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd}, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, booktitle = {AIRWeb '08: Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web}, publisher = {ACM}, address = {New York, NY, USA}, year = {2008}, pages = {61--68}, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, doi = {10.1145/1451983.1451998}, isbn = {978-1-60558-159-0}, keywords = {2008, bookmarking, detection, itegpub, l3s, myown, seminar, spam, summer}, abstract = {The annotation of web sites in social bookmarking systemshas become a popular way to manage and find informationon the web. The community structure of such systems attractsspammers: recent post pages, popular pages or specifictag pages can be manipulated easily. As a result, searchingor tracking recent posts does not deliver quality resultsannotated in the community, but rather unsolicited, oftencommercial, web sites. To retain the benefits of sharingone’s web content, spam-fighting mechanisms that can facethe flexible strategies of spammers need to be developed.} }

%0 = inproceedings %A = Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd %B = AIRWeb '08: Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web %C = New York, NY, USA %D = 2008 %I = ACM %T = The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems %U = http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf