@inproceedings{suchanek2008social, abstract = {This paper aims to quantify two common assumptions about social tagging: (1) that tags are "meaningful" and (2) that the tagging process is influenced by tag suggestions. For (1), we analyze the semantic properties of tags and the relationship between the tags and the content of the tagged page. Our analysis is based on a corpus of search keywords, contents, titles, and tags applied to several thousand popular Web pages. Among other results, we find that the more popular tags of a page tend to be the more meaningful ones. For (2), we develop a model of how the influence of tag suggestions can be measured. From a user study with over 4,000 participants, we conclude that roughly one third of the tag applications may be induced by the suggestions. Our results would be of interest for designers of social tagging systems and are a step towards understanding how to best leverage social tags for applications such as search and information extraction.}, acmid = {1458114}, address = {New York, NY, USA}, author = {Suchanek, Fabian M. and Vojnovic, Milan and Gunawardena, Dinan}, booktitle = {Proceeding of the 17th ACM conference on Information and knowledge management}, doi = {10.1145/1458082.1458114}, interhash = {1bca5a66a6a562258e0c0357545fed34}, intrahash = {ff31cf8541004adc7cd712ed715706b3}, isbn = {978-1-59593-991-3}, location = {Napa Valley, California, USA}, numpages = {10}, pages = {223--232}, publisher = {ACM}, series = {CIKM '08}, title = {Social tags: meaning and suggestions}, url = {http://doi.acm.org/10.1145/1458082.1458114}, year = 2008 } @incollection{radelaar2011improving, affiliation = {Erasmus University Rotterdam, PO Box 1738, NL-3000 Rotterdam, The Netherlands}, author = {Radelaar, Joni and Boor, Aart-Jan and Vandic, Damir and van Dam, Jan-Willem and Hogenboom, Frederik and Frasincar, Flavius}, booktitle = {Web Engineering}, editor = {Auer, Sören and Díaz, Oscar and Papadopoulos, George}, interhash = {48fe306f42bc405a5f8ae0f4a8885f3a}, intrahash = {77bc7f7e46481b47c11dd9e53d5741e0}, note = {10.1007/978-3-642-22233-7_19}, pages = {274-288}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, title = {Improving the Exploration of Tag Spaces Using Automated Tag Clustering}, url = {http://dx.doi.org/10.1007/978-3-642-22233-7_19}, volume = 6757, year = 2011 } @inproceedings{widdows2002graph, author = {Widdows, Dominic and Dorow, Beate}, bibsource = {DBLP, http://dblp.uni-trier.de}, booktitle = {COLING}, ee = {http://acl.ldc.upenn.edu/C/C02/C02-1114.pdf}, interhash = {778db99ef80f4b5a682eb6923cc0eb13}, intrahash = {a16325d6196b3adb8e68851f4f4eff84}, title = {A Graph Model for Unsupervised Lexical Acquisition}, year = 2002 } @inproceedings{krestel2008art, abstract = {

Collaborative tagging, supported by many social networking websites, is currently enjoying an increasing popularity. The usefulness of this largely available tag data has been explored in many applications including web resources categorization,deriving emergent semantics, web search etc. However, since tags are supplied by users <em>freely</em> , not all of them are useful and reliable, especially when they are generated by spammers with malicious intent. Therefore, identifying tags of high quality is crucial in improving the performance of applications based on tags. In this paper, we propose TRP-Rank (Tag-Resource Pair Rank), an algorithm to measure the quality of tags by manually assessing a seed set and <em>propagating the quality</em> through a graph. The three dimensional relationship among users, tags and web resources is firstly represented by a graph structure. A set of seed nodes, where each node represents a tag annotating a resource, is then selected and their quality is assessed. The quality of the remaining nodes is calculated by propagating the known quality of the seeds through the graph structure. We evaluate our approach on a public data set where tags generated by suspicious spammers were manually labelled. The experimental results demonstrate the effectiveness of this approach in measuring the quality of tags.

}, acmid = {1484165}, address = {Berlin, Heidelberg}, author = {Krestel, Ralf and Chen, Ling}, booktitle = {Proceedings of the 3rd Asian Semantic Web Conference on The Semantic Web}, doi = {10.1007/978-3-540-89704-0_18}, interhash = {44401088956f59c92c11f6a910ed4df4}, intrahash = {dc00da9179d556ce047c1b41eb815e21}, isbn = {978-3-540-89703-3}, location = {Bangkok, Thailand}, numpages = {15}, pages = {257--271}, publisher = {Springer-Verlag}, series = {ASWC '08}, title = {The Art of Tagging: Measuring the Quality of Tags}, url = {http://dx.doi.org/10.1007/978-3-540-89704-0_18}, year = 2008 } @inproceedings{illigtoappearcomparison, author = {Illig, Jens and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, booktitle = {Postproceedings of the International Conference on Knowledge Processing in Practice (KPP2007)}, file = {:illig2009comparison.pdf:PDF}, interhash = {849cc8141815da667268acd7389d610a}, intrahash = {65f66d8e45722648f0471a193dd8ead6}, publisher = {Springer}, title = {A Comparison of content-based Tag Recommendations in Folksonomy Systems}, year = {to appear} } @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 }