Collaborative tagging systems--systems where many casual users annotate objects with free-form strings (tags) of their choosing--have recently emerged as a powerful way to label and organize large collections of data. During our recent investigation into these types of systems, we discovered a simple but remarkably effective algorithm for converting a large corpus of tags annotating objects in a tagging system into a navigable hierarchical taxonomy of tags. We first discuss the algorithm and then present a preliminary model to explain why it is so effective in these types of systems.

@techreport{citeulike:739394, author = {Heymann, Paul and Garcia-Molina, Hector}, title = {Collaborative Creation of Communal Hierarchical Taxonomies in Social Tagging Systems}, school = {Standford University}, year = {2006}, number = {2006-10}, url = {http://dbpubs.stanford.edu:8090/pub/2006-10}, keywords = {clustering, collaborative, folksonomy, kdubiq, ol, social, sosbuch, summerschool, tagging, taggingsurvey, taxonomy, webzu}, abstract = {Collaborative tagging systems---systems where many casual users annotate objects with free-form strings (tags) of their choosing---have recently emerged as a powerful way to label and organize large collections of data. During our recent investigation into these types of systems, we discovered a simple but remarkably effective algorithm for converting a large corpus of tags annotating objects in a tagging system into a navigable hierarchical taxonomy of tags. We first discuss the algorithm and then present a preliminary model to explain why it is so effective in these types of systems.} }

%0 = techreport %A = Heymann, Paul and Garcia-Molina, Hector %D = 2006 %T = Collaborative Creation of Communal Hierarchical Taxonomies in Social Tagging Systems %U = http://dbpubs.stanford.edu:8090/pub/2006-10

@inproceedings{schmitz06, author = {Schmitz, Patrick}, title = {Inducing Ontology from Flickr Tags.}, booktitle = {Collaborative Web Tagging Workshop at WWW2006, Edinburgh, Scotland}, year = {2006}, url = {http://www.ibiblio.org/www_tagging/2006/22.pdf}, keywords = {clustering, folksonomy, learning, ol, ontology, semantic, sosbuch, tagging, taggingsurvey, toread, webzu} }

%0 = inproceedings %A = Schmitz, Patrick %B = Collaborative Web Tagging Workshop at WWW2006, Edinburgh, Scotland %D = 2006 %T = Inducing Ontology from Flickr Tags. %U = http://www.ibiblio.org/www_tagging/2006/22.pdf

@book{cimiano2006, author = {Cimiano, Philipp}, title = {Ontology Learning and Population from Text: Algorithms, Evaluation and Applications}, publisher = {Springer-Verlag New York, Inc.}, address = {Secaucus, NJ, USA}, year = {2006}, url = {http://portal.acm.org/citation.cfm?id=1177318}, isbn = {0387306323}, keywords = {ol, text, webzu} }

%0 = book %A = Cimiano, Philipp %C = Secaucus, NJ, USA %D = 2006 %I = Springer-Verlag New York, Inc. %T = Ontology Learning and Population from Text: Algorithms, Evaluation and Applications %U = http://portal.acm.org/citation.cfm?id=1177318

@inproceedings{Benz07OL, author = {Benz, Dominik and Hotho, Andreas}, title = {Position Paper: Ontology Learning from Folksonomies.}, editor = {Hinneburg, Alexander}, booktitle = {LWA 2007: Lernen - Wissen - Adaption, Halle, September 2007, Workshop Proceedings (LWA)}, publisher = {Martin-Luther-University Halle-Wittenberg}, year = {2007}, pages = {109-112}, url = {http://dblp.uni-trier.de/db/conf/lwa/lwa2007.html#BenzH07}, isbn = {978-3-86010-907-6}, keywords = {2007, folksonomy, kdubiq, learning, myown, ol, ontology, summerschool, webzu} }

%0 = inproceedings %A = Benz, Dominik and Hotho, Andreas %B = LWA 2007: Lernen - Wissen - Adaption, Halle, September 2007, Workshop Proceedings (LWA) %D = 2007 %I = Martin-Luther-University Halle-Wittenberg %T = Position Paper: Ontology Learning from Folksonomies. %U = http://dblp.uni-trier.de/db/conf/lwa/lwa2007.html#BenzH07

Social tagging systems have recently became very popular as a means to classify large sets of resources shared among on-line communities over the social Web. However, the folksonomies resulting from the use of these systems revealed limitations : tags are ambiguous and their spelling may vary, and folksonomies are difficult to exploit in order to retrieve or exchange information. This article compares the recent attempts to overcome these limitations and to support the use of folksonomies with formal languages and ontologies from the Semantic Web.

@article{4686305, author = {Limpens, Freddy and Gandon, Fabien and Buffa, Michel}, title = {Bridging ontologies and folksonomies to leverage knowledge sharing on the social Web: A brief survey}, journal = {Automated Software Engineering - Workshops, 2008. ASE Workshops 2008. 23rd IEEE/ACM International Conference on}, year = {2008}, pages = {13-18}, doi = {10.1109/ASEW.2008.4686305}, keywords = {folksonomy, ol, ontology, survey, toread, webzu}, abstract = {Social tagging systems have recently became very popular as a means to classify large sets of resources shared among on-line communities over the social Web. However, the folksonomies resulting from the use of these systems revealed limitations : tags are ambiguous and their spelling may vary, and folksonomies are difficult to exploit in order to retrieve or exchange information. This article compares the recent attempts to overcome these limitations and to support the use of folksonomies with formal languages and ontologies from the Semantic Web.} }

%0 = article %A = Limpens, Freddy and Gandon, Fabien and Buffa, Michel %D = 2008 %T = Bridging ontologies and folksonomies to leverage knowledge sharing on the social Web: A brief survey

Wikipedia is a goldmine of information; not just for its many readers, but
so for the growing community of researchers who recognize it as a resource of
ceptional scale and utility. It represents a vast investment of manual effort
d judgment: a huge, constantly evolving tapestry of concepts and relations
at is being applied to a host of tasks.
This article provides a comprehensive description of this work. It focuses on
search that extracts and makes use of the concepts, relations, facts and
scriptions found in Wikipedia, and organizes the work into four broad
tegories: applying Wikipedia to natural language processing; using it to
cilitate information retrieval and information extraction; and as a resource
r ontology building. The article addresses how Wikipedia is being used as is,
w it is being improved and adapted, and how it is being combined with other
ructures to create entirely new resources. We identify the research groups
d individuals involved, and how their work has developed in the last few
ars. We provide a comprehensive list of the open-source software they have
oduced. We also discuss the implications of this work for the long-awaited
mantic web.

@misc{Medelyan2008, author = {Medelyan, Olena and Legg, Catherine and Milne, David and Witten, Ian H.}, title = {Mining Meaning from Wikipedia}, year = {2008}, note = {cite arxiv:0809.4530
mment: An extensive survey of re-using information in Wikipedia in natural
language processing, information retreival and extraction and ontology
building. submitted}, url = {http://arxiv.org/abs/0809.4530}, keywords = {mining, ol, relation, semantic, webzu, wikipedia}, abstract = { Wikipedia is a goldmine of information; not just for its many readers, but
so for the growing community of researchers who recognize it as a resource of
ceptional scale and utility. It represents a vast investment of manual effort
d judgment: a huge, constantly evolving tapestry of concepts and relations
at is being applied to a host of tasks.
This article provides a comprehensive description of this work. It focuses on
search that extracts and makes use of the concepts, relations, facts and
scriptions found in Wikipedia, and organizes the work into four broad
tegories: applying Wikipedia to natural language processing; using it to
cilitate information retrieval and information extraction; and as a resource
r ontology building. The article addresses how Wikipedia is being used as is,
w it is being improved and adapted, and how it is being combined with other
ructures to create entirely new resources. We identify the research groups
d individuals involved, and how their work has developed in the last few
ars. We provide a comprehensive list of the open-source software they have
oduced. We also discuss the implications of this work for the long-awaited
mantic web.
} }

%0 = misc %A = Medelyan, Olena and Legg, Catherine and Milne, David and Witten, Ian H. %D = 2008 %T = Mining Meaning from Wikipedia %U = http://arxiv.org/abs/0809.4530

Abstract  Ontology is one of the fundamental cornerstones of the semantic Web. The pervasive use of ontologies in information sharing
d knowledge management calls for efficient and effective approaches to ontology development. Ontology learning, which seeksto discover ontological knowledge from various forms of data automatically or semi-automatically, can overcome the bottleneckof ontology acquisition in ontology development. Despite the significant progress in ontology learning research over the pastdecade, there remain a number of open problems in this field. This paper provides a comprehensive review and discussion ofmajor issues, challenges, and opportunities in ontology learning. We propose a new learning-oriented model for ontology developmentand a framework for ontology learning. Moreover, we identify and discuss important dimensions for classifying ontology learningapproaches and techniques. In light of the impact of domain on choosing ontology learning approaches, we summarize domaincharacteristics that can facilitate future ontology learning effort. The paper offers a road map and a variety of insightsabout this fast-growing field.

@article{keyhere, author = {Zhou, Lina}, title = {Ontology learning: state of the art and open issues}, journal = {Information Technology and Management}, year = {2007}, volume = {8}, number = {3}, pages = {241--252}, url = {http://dx.doi.org/10.1007/s10799-007-0019-5}, keywords = {learning, ol, ontology, survey, webzu}, abstract = {Abstract  Ontology is one of the fundamental cornerstones of the semantic Web. The pervasive use of ontologies in information sharing and knowledge management calls for efficient and effective approaches to ontology development. Ontology learning, which seeksto discover ontological knowledge from various forms of data automatically or semi-automatically, can overcome the bottleneckof ontology acquisition in ontology development. Despite the significant progress in ontology learning research over the pastdecade, there remain a number of open problems in this field. This paper provides a comprehensive review and discussion ofmajor issues, challenges, and opportunities in ontology learning. We propose a new learning-oriented model for ontology developmentand a framework for ontology learning. Moreover, we identify and discuss important dimensions for classifying ontology learningapproaches and techniques. In light of the impact of domain on choosing ontology learning approaches, we summarize domaincharacteristics that can facilitate future ontology learning effort. The paper offers a road map and a variety of insightsabout this fast-growing field.} }

%0 = article %A = Zhou, Lina %D = 2007 %T = Ontology learning: state of the art and open issues %U = http://dx.doi.org/10.1007/s10799-007-0019-5

@article{1356291, author = {Meyer, M. and Rensing, C. and Steinmetz, R.}, title = {Using community & generated contents as a substitute corpus for metadata generation}, journal = {Int. J. Adv. Media Commun.}, publisher = {Inderscience Publishers}, address = {Inderscience Publishers, Geneva, SWITZERLAND}, year = {2008}, volume = {2}, number = {1}, pages = {59--72}, url = {http://portal.acm.org/citation.cfm?id=1356291}, doi = {http://dx.doi.org/10.1504/IJAMC.2008.016758}, issn = {1462-4613}, keywords = {elearning, ol, webzu, wikipedia} }

%0 = article %A = Meyer, M. and Rensing, C. and Steinmetz, R. %C = Inderscience Publishers, Geneva, SWITZERLAND %D = 2008 %I = Inderscience Publishers %T = Using community & generated contents as a substitute corpus for metadata generation %U = http://portal.acm.org/citation.cfm?id=1356291