@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{markines2009evaluating, abstract = {Social bookmarking systems and their emergent information structures, known as folksonomies, are increasingly important data sources for Semantic Web applications. A key question for harvesting semantics from these systems is how to extend and adapt traditional notions of similarity to folksonomies, and which measures are best suited for applications such as navigation support, semantic search, and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures derived from established information-theoretic, statistical, and practical measures. Our framework deals generally and symmetrically with users, tags, and resources. For evaluation purposes we focus on similarity among tags and resources, considering different ways to aggregate annotations across users. After comparing how tag similarity measures predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory. We also investigate the issue of scalability. We ?nd that mutual information with distributional micro-aggregation across users yields the highest accuracy, but is not scalable; per-user projection with collaborative aggregation provides the best scalable approach via incremental computations. The results are consistent across resource and tag similarity.}, author = {Markines, Benjamin and Cattuto, Ciro and Menczer, Filippo and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {18th International World Wide Web Conference}, file = {markines2009evaluating.pdf:markines2009evaluating.pdf:PDF}, groups = {public}, interhash = {a266558ad4d83d536a0be2ac94b6b7df}, intrahash = {d16e752a8295d5dad7e26b199d9f614f}, month = {April}, pages = {641--641}, title = {Evaluating Similarity Measures for Emergent Semantics of Social Tagging}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/markines2009evaluating.pdf}, username = {dbenz}, year = 2009 } @inproceedings{giannakidou2008coclustering, abstract = {Under social tagging systems, a typical Web 2.0 application, users label digital data sources by using freely chosen textual descriptions (tags). Poor retrieval in the aforementioned systems remains a major problem mostly due to questionable tag validity and tag ambiguity. Earlier clustering techniques have shown limited improvements, since they were based mostly on tag co-occurrences. In this paper, a co-clustering approach is employed, that exploits joint groups of related tags and social data sources, in which both social and semantic aspects of tags are considered simultaneously. Experimental results demonstrate the efficiency and the beneficial outcome of the proposed approach in correlating relevant tags and resources.}, author = {Giannakidou, Eirini and Koutsonikola, Vassiliki A. and Vakali, Athena and Kompatsiaris, Yiannis}, booktitle = {WAIM}, crossref = {conf/waim/2008}, ee = {http://dx.doi.org/10.1109/WAIM.2008.61}, file = {giannakidou2008coclustering.pdf:giannakidou2008coclustering.pdf:PDF}, groups = {public}, interhash = {bf55ee73fa8e8e370cffe8ef7bb9cd60}, intrahash = {2b24046689df977f7853b557c04689f3}, isbn = {978-0-7695-3185-4}, pages = {317-324}, publisher = {IEEE}, timestamp = {2011-02-17 11:00:40}, title = {Co-Clustering Tags and Social Data Sources.}, url = {http://dblp.uni-trier.de/db/conf/waim/waim2008.html#GiannakidouKVK08}, username = {dbenz}, year = 2008 } @inproceedings{ireson2010toponym, abstract = {Increasingly user-generated content is being utilised as a source of information, however each individual piece of content tends to contain low levels of information. In addition, such information tends to be informal and imperfect in nature; containing imprecise, subjective, ambiguous expressions. However the content does not have to be interpreted in isolation as it is linked, either explicitly or implicitly, to a network of interrelated content; it may be grouped or tagged with similar content, comments may be added by other users or it may be related to other content posted at the same time or by the same author or members of the author's social network. This paper generally examines how ambiguous concepts within user-generated content can be assigned a specific/formal meaning by considering the expanding context of the information, i.e. other information contained within directly or indirectly related content, and specifically considers the issue of toponym resolution of locations.}, author = {Ireson, Neil and Ciravegna, Fabio}, booktitle = {#iswc2010#}, crossref = {conf/semweb/2010-1}, editor = {Patel-Schneider, Peter F. and Pan, Yue and Hitzler, Pascal and Mika, Peter and Zhang, Lei and Pan, Jeff Z. and Horrocks, Ian and Glimm, Birte}, ee = {http://dx.doi.org/10.1007/978-3-642-17746-0_24}, file = {ireson2010toponym.pdf:ireson2010toponym.pdf:PDF}, groups = {public}, interhash = {fd064c5fb724a5a72a6a67d1f6a7f8df}, intrahash = {1b0c968b68745971cef000eb3644ba3a}, isbn = {978-3-642-17745-3}, pages = {370-385}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2011-02-02 15:00:36}, title = {Toponym Resolution in Social Media.}, url = {http://dblp.uni-trier.de/db/conf/semweb/iswc2010-1.html#IresonC10}, username = {dbenz}, volume = 6496, year = 2010 } @inproceedings{specia2007integrating, abstract = {While tags in collaborative tagging systems serve primarily an indexing purpose, facilitating search and navigation of resources, the use of the same tags by more than one individual can yield a collective classification schema. We present an approach for making explicit the semantics behind the tag space in social tagging systems, so that this collaborative organization can emerge in the form of groups of concepts and partial ontologies. This is achieved by using a combination of shallow pre-processing strategies and statistical techniques together with knowledge provided by ontologies available on the semantic web. Preliminary results on the del.icio.us and Flickr tag sets show that the approach is very promising: it generates clusters with highly related tags corresponding to concepts in ontologies and meaningful relationships among subsets of these tags can be identified.}, author = {Specia, Lucia and Motta, Enrico}, file = {specia2007integrating.pdf:specia2007integrating.pdf:PDF}, groups = {public}, interhash = {b828fbd5c9ddc4f9551f973445ecb283}, intrahash = {8800fc1a639aeb43fd55598d2410e2e1}, pages = {624-639}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {2007-09-29 15:16:09}, title = {Integrating Folksonomies with the Semantic Web}, username = {dbenz}, volume = {4519/2007}, year = 2007 } @incollection{jung2010matching, abstract = {By taking into account various co-occurence patterns from a folksonomy, semantic correspondences between tags have been discovered and applied to a number of applications (e.g., recommendation). In this paper, we propose a novel collective intelligence application for expanding and transforming queries for searching for multilingual resources. Thereby, multilingual tags (e.g., between ‘Seoul’ in English and ‘Coree’ in French) within a folksonomy have been analyzed whether they have a significant relationship or not. We have tested the proposed multilingual tag matching method by collecting real-world tagging information from several well-known social tagging websites (e.g., Del.icio.us), and applied to translating queries to other languages without any external dictionary.}, address = {Berlin / Heidelberg}, affiliation = {Knowledge Engineering Laboratory, Department of Computer Engineering, Yeungnam University, Gyeongsan, Korea 712-749}, author = {Jung, Jason}, booktitle = {Trends in Applied Intelligent Systems}, doi = {10.1007/978-3-642-13025-0_5}, editor = {García-Pedrajas, Nicolás and Herrera, Francisco and Fyfe, Colin and Benítez, José and Ali, Moonis}, file = {jung2010matching.pdf:jung2010matching.pdf:PDF}, groups = {public}, interhash = {ac7f29839d16807427051b94a427c2ab}, intrahash = {7dabc4ff8924c6054ac31f921cf5396a}, pages = {39-46}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2011-02-09 01:42:55}, title = {Matching Multilingual Tags Based on Community of Lingual Practice from Multiple Folksonomy: A Preliminary Result}, url = {http://dx.doi.org/10.1007/978-3-642-13025-0_5}, username = {dbenz}, volume = 6097, year = 2010 } @inproceedings{schmitz2006mining, abstract = {Social bookmark tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. These systems provide currently relatively few structure. We discuss in this paper, how association rule mining can be adopted to analyze and structure folksonomies, and how the results can be used for ontology learning and supporting emergent semantics. We demonstrate our approach on a large scale dataset stemming from an online system.}, address = {Heidelberg}, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, booktitle = {Data Science and Classification. Proceedings of the 10th IFCS Conf.}, editor = {Batagelj, V. and Bock, H.-H. and Ferligoj, A. and �iberna, A.}, file = {schmitz2006mining.pdf:schmitz2006mining.pdf:PDF}, groups = {public}, interhash = {9f407e0b779aba5b3afca7fb906f579b}, intrahash = {ed504c16bc4eb561a9446bd98b10dca1}, lastdatemodified = {2006-12-07}, lastname = {Schmitz}, month = {July}, own = {notown}, pages = {261--270}, pdf = {schmitz06-mining.pdf}, publisher = {Springer}, read = {notread}, series = {Studies in Classification, Data Analysis, and Knowledge Organization}, timestamp = {2007-09-11 13:31:35}, title = {Mining Association Rules in Folksonomies}, username = {dbenz}, year = 2006 } @article{ryu2009toward, abstract = {This paper describes new thesaurus construction method in which class-based, small size thesauruses are constructed and merged as a whole based on domain classification system. This method has advantages in that 1) taxonomy construction complexity is reduced, 2) each class-based thesaurus can be reused in other domain thesaurus, and 3) term distribution per classes in target domain is easily identified. The method is composed of three steps: term extraction step, term classification step, and taxonomy construction step. All steps are balanced approaches of automatic processing and manual verification. We constructed Korean IT domain thesaurus based on proposed method. Because terms are extracted from Korean newspaper and patent corpus in IT domain, the thesaurus includes many Korean neologisms. The thesaurus consists of 81 upper level classes and over 1,000 IT terms.}, author = {Ryu, P.M. and Kim, J.H. and Nam, Y. and Huang, J.X. and Shin, S. and Lee, S.M. and Choi, K.S.}, file = {ryu2009toward.pdf:ryu2009toward.pdf:PDF}, groups = {public}, interhash = {33037e9884a62f1994c9d45eb68c27e7}, intrahash = {bd4f375366e49a3eb31e60b268dca01c}, journal = {Relation}, journalpub = {1}, number = {1.129}, pages = 7396, publisher = {Citeseer}, timestamp = {2010-11-09 12:05:09}, title = {{Toward Domain Specific Thesaurus Construction: Divide-and-Conquer Method}}, url = {http://scholar.google.de/scholar.bib?q=info:4K_xIsqmea0J:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=9}, username = {dbenz}, volume = 10, year = 2009 } @inproceedings{auyeung2007tag, abstract = {Collaborative tagging systems are becoming very popular recently. Web users use freely-chosen tags to describe shared resources, resulting in a folksonomy. One problem of folksonomies is that tags which appear in the same form may carry multiple meanings and represent different concepts. As this kind of tags are ambiguous, the precisions in both description and retrieval of the shared resources are reduced. We attempt to develop effective methods to disambiguate tags by studying the tripartite structure of folksonomies. This paper describes the network analysis techniques that we employ to discover clusters of nodes in networks and the algorithm for tag disambiguation. Experiments show that the method is very effective in performing the task.}, author = {man Au Yeung, Ching and Gibbins, Nicholas and Shadbolt, Nigel}, bibdate = {2008-02-06}, bibsource = {DBLP, http://dblp.uni-trier.de/db/conf/iat/iatw2007.html#YeungGS07}, booktitle = {Web Intelligence/IAT Workshops}, crossref = {conf/iat/2007w}, file = {auyeung2007tag.pdf:auyeung2007tag.pdf:PDF}, groups = {public}, interhash = {715a5b5e7a4d3dca918e89e9be7a77fb}, intrahash = {a7e6e642d676b6ce9b5e5b3a4d350eac}, pages = {3--6}, publisher = {IEEE}, timestamp = {2010-11-30 18:26:37}, title = {Tag Meaning Disambiguation through Analysis of Tripartite Structure of Folksonomies}, url = {http://dx.doi.org/10.1109/WIIATW.2007.4427527}, username = {dbenz}, year = 2007 } @inproceedings{brooks2006improved, abstract = {Tags have recently become popular as a means of annotating and organizing Web pages and blog entries. Advocates of tagging argue that the use of tags produces a 'folksonomy', a system in which the meaning of a tag is determined by its use among the community as a whole. We analyze the effectiveness of tags for classifying blog entries by gathering the top 350 tags from Technorati and measuring the similarity of all articles that share a tag. We find that tags are useful for grouping articles into broad categories, but less effective in indicating the particular content of an article. We then show that automatically extracting words deemed to be highly relevant can produce a more focused categorization of articles. We also show that clustering algorithms can be used to reconstruct a topical hierarchy among tags, and suggest that these approaches may be used to address some of the weaknesses in current tagging systems.}, address = {New York, NY, USA}, author = {Brooks, Christopher H. and Montanez, Nancy}, booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web}, file = {:brooks06-improved.pdf:PDF;brooks2006improved.pdf:brooks2006improved.pdf:PDF}, groups = {public}, interhash = {c88a665abf8d88c5a7ae95fa2783f837}, intrahash = {5c9c83e89da2faa8906a5927fe7ca3ef}, lastdatemodified = {2006-07-18}, lastname = {Brooks}, longnotes = {[[http://www2006.org/programme/files/pdf/583-slides.pdf slides]] Summary: - authors analyse the effectiveness of tags for classifying blog articles (technorati) - clustering of articles beloning to top 350 technorati tags * by tag * randomly * by related by Google News - results: * tags help to classify articles into broad categories (yet Google News performs better) * tags are not that descriptive for a specific topic of an article * automatically extracted tags (by TF/IDF) are much more descriptive for specific content - 2nd study: hierarchical clustering of articles (starting from tag clusters, i.e. all articles who share a tag) - resulting tag hierarchy comes close to e.g. Yahoo hand-built one}, own = {own}, pages = {625--632}, pdf = {brooks06-improved.pdf}, publisher = {ACM Press}, read = {read}, timestamp = {2009-09-29 16:23:07}, title = {Improved annotation of the blogosphere via autotagging and hierarchical clustering}, url = {http://www2006.org/programme/item.php?id=583}, username = {dbenz}, year = 2006 } @article{gemmell2008personalizing, abstract = {The popularity of collaborative tagging, otherwise known as “folksonomies�?, emanate from the flexibility they afford usersin navigating large information spaces for resources, tags, or other users, unencumbered by a pre-defined navigational orconceptual hierarchy. Despite its advantages, social tagging also increases user overhead in search and navigation: usersare free to apply any tag they wish to a resource, often resulting in a large number of tags that are redundant, ambiguous,or idiosyncratic. Data mining techniques such as clustering provide a means to overcome this problem by learning aggregateuser models, and thus reducing noise. In this paper we propose a method to personalize search and navigation based on unsupervisedhierarchical agglomerative tag clustering. Given a user profile, represented as a vector of tags, the learned tag clustersprovide the nexus between the user and those resources that correspond more closely to the user’s intent. We validate thisassertion through extensive evaluation of the proposed algorithm using data from a real collaborative tagging Web site.}, author = {Gemmell, Jonathan and Shepitsen, Andriy and Mobasher, Bamshad and Burke, Robin}, file = {gemmell2008personalizing.pdf:gemmell2008personalizing.pdf:PDF}, groups = {public}, interhash = {e544ba095f411429896b11fd3f94fd5c}, intrahash = {2e0535788c372e98e49646873cea4e1e}, journal = {Data Warehousing and Knowledge Discovery}, journalpub = {1}, pages = {196--205}, timestamp = {2009-08-10 10:30:08}, title = {Personalizing Navigation in Folksonomies Using Hierarchical Tag Clustering}, url = {http://dx.doi.org/10.1007/978-3-540-85836-2_19}, username = {dbenz}, year = 2008 } @inproceedings{mika2005ontologies, abstract = {In our work we extend the traditional bipartite model of ontologies with the social dimension, leading to a tripartite model of actors, concepts and instances. We demonstrate the application of this representation by showing how community-based semantics emerges from this model through a process of graph transformation. We illustrate ontology emergence by two case studies, an analysis of a large scale folksonomy system and a novel method for the extraction of community-based ontologies from Web pages.}, author = {Mika, Peter}, booktitle = {The Semantic Web - ISWC 2005, Proceedings of the 4th International Semantic Web Conference, ISWC 2005, Galway, Ireland, November 6-10}, editor = {Gil, Yolanda and Motta, Enrico and Benjamins, V. Richard and Musen, Mark A.}, file = {mika2005ontologies.pdf:mika2005ontologies.pdf:PDF}, groups = {public}, interhash = {5ea12110b5bb0e3a8ad09aeb16a70cdb}, intrahash = {426c2fd559bb4e41c4f67d4eed0a39c7}, lastdatemodified = {2006-09-26}, lastname = {Mika}, longnotes = {[[http://citeseer.ist.psu.edu/739485.html citeseer]]}, own = {notown}, pages = {522-536}, pdf = {mika05-ontologies.pdf}, publisher = {Springer}, read = {notread}, series = {Lecture Notes in Computer Science}, timestamp = {2007-09-11 13:31:32}, title = {Ontologies Are Us: A Unified Model of Social Networks and Semantics.}, url = {http://dx.doi.org/10.1007/11574620_38}, username = {dbenz}, volume = 3729, year = 2005 } @inproceedings{tang2009towards, abstract = {A folksonomy refers to a collection of user-defined tags with which users describe contents published on the Web. With the flourish of Web 2.0, folksonomies have become an important mean to develop the Semantic Web. Because tags in folksonomies are authored freely, there is a need to understand the structure and semantics of these tags in various applications. In this paper, we propose a learning approach to create an ontology that captures the hierarchical semantic structure of folksonomies. Our experimental results on two different genres of real world data sets show that our method can effectively learn the ontology structure from the folksonomies.}, address = {San Francisco, CA, USA}, author = {Tang, Jie and fung Leung, Ho and Luo, Qiong and Chen, Dewei and Gong, Jibin}, booktitle = {IJCAI'09: Proceedings of the 21st international jont conference on Artifical intelligence}, file = {tang2009towards.pdf:tang2009towards.pdf:PDF}, groups = {public}, interhash = {17f95a6ba585888cf45443926d8b7e98}, intrahash = {7b335f08a288a79eb70eff89f1ec7630}, location = {Pasadena, California, USA}, pages = {2089--2094}, publisher = {Morgan Kaufmann Publishers Inc.}, timestamp = {2009-12-23 21:30:44}, title = {Towards ontology learning from folksonomies}, url = {http://ijcai.org/papers09/Papers/IJCAI09-344.pdf}, username = {dbenz}, year = 2009 } @inproceedings{wu2006exploring, abstract = {In order to obtain a machine understandable semantics for web resources, research on the Semantic Web tries to an- notate web resources with concepts and relations from ex- plicitly de¯ned formal ontologies. This kind of formal an- notation is usually done manually or semi-automatically. In this paper, we explore a complement approach that focuses on the \social annotations of the web" which are annota- tions manually made by normal web users without a pre- de¯ned formal ontology. Compared to the formal annota- tions, although social annotations are coarse-grained, infor- mal and vague, they are also more accessible to more peo- ple and better re°ect the web resources' meaning from the users' point of views during their actual usage of the web re- sources. Using a social bookmark service as an example, we show how emergent semantics [2] can be statistically derived from the social annotations. Furthermore, we apply the de- rived emergent semantics to discover and search shared web bookmarks. The initial evaluation on our implementation shows that our method can e®ectively discover semantically related web bookmarks that current social bookmark service can not discover easily.}, address = {New York, NY, USA}, author = {Wu, Xian and Zhang, Lei and Yu, Yong}, booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web}, file = {wu2006exploring.pdf:wu2006exploring.pdf:PDF}, groups = {public}, interhash = {478741551c92402f539a90a9caed61b6}, intrahash = {2ff38a7f8e9e3941d0598877fe964eb5}, lastdatemodified = {2007-01-04}, lastname = {Wu}, own = {notown}, pages = {417--426}, pdf = {wu06-exploring.pdf}, publisher = {ACM Press}, read = {notread}, timestamp = {2007-09-11 13:31:41}, title = {Exploring social annotations for the semantic web}, url = {http://doi.acm.org/10.1145/1135777.1135839}, username = {dbenz}, year = 2006 } @inproceedings{jaeschke2006trias, abstract = {In this paper, we present the foundations for mining frequent tri-concepts, which extend the notion of closed itemsets to three-dimensional data to allow for mining folksonomies. We provide a formal definition of the problem, and present an efficient algorithm for its solution as well as experimental results on a large real-world example.}, address = {Hong Kong}, author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd}, booktitle = {Proceedings of the 6th IEEE International Conference on Data Mining (ICDM 06)}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICDM.2006.162}, file = {jaeschke2006trias.pdf:jaeschke2006trias.pdf:PDF}, groups = {public}, interhash = {b4964c3bdd2991a80873d7080ef6a73e}, intrahash = {e387c294129e11f4221514d5fa807e26}, isbn = {0-7695-2701-9}, issn = {1550-4786}, month = {December}, pages = {907-911}, publisher = {IEEE Computer Society}, timestamp = {2010-11-10 15:35:25}, title = {TRIAS - An Algorithm for Mining Iceberg Tri-Lattices}, url = {http://www.kde.cs.uni-kassel.de/jaeschke/paper/jaeschke06trias.pdf}, username = {dbenz}, vgwort = {19}, year = 2006 } @article{jaeschke2008discovering, abstract = {Social bookmarking tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. Unlike ontologies, shared conceptualizations are not formalized, but rather implicit. We present a new data mining task, the mining of all frequent tri-concepts, together with an efficient algorithm, for discovering these implicit shared conceptualizations. Our approach extends the data mining task of discovering all closed itemsets to three-dimensional data structures to allow for mining folksonomies. We provide a formal definition of the problem, and present an efficient algorithm for its solution. Finally, we show the applicability of our approach on three large real-world examples.}, address = {New York}, author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd}, booktitle = {Semantic Web and Web 2.0}, doi = {10.1016/j.websem.2007.11.004}, editor = {Finin, T. and Mizoguchi, R. and Staab, S.}, file = {jaeschke2008discovering.pdf:jaeschke2008discovering.pdf:PDF}, groups = {public}, interhash = {cfca594f9dbe30694bfbcdeb40dc4e88}, intrahash = {18e8babe208fae2c0342438617b0ec31}, issn = {1570-8268}, journal = {Web Semantics: Science, Services and Agents on the World Wide Web}, journalpub = {1}, month = feb, number = 1, pages = {38--53}, publisher = {Elsevier}, timestamp = {2010-11-10 15:35:25}, title = {Discovering Shared Conceptualizations in Folksonomies}, url = {http://www.sciencedirect.com/science/article/B758F-4R53WD4-1/2/ae56bd6e7132074272ca2035be13781b}, username = {dbenz}, vgwort = {59}, volume = 6, year = 2008 } @incollection{lin2009integrateda, abstract = {Collaborative tagging systems have recently emerged as one of the rapidly growing web 2.0 applications. The informal social classification structure in these systems, also known as folksonomy, provides a convenient way to annotate resources by allowing users to use any keyword or tag that they find relevant. In turn, the flat and non-hierarchical structure with unsupervised vocabularies leads to low search precision and poor resource navigation and retrieval. This drawback has created the need for ontological structures which provide shared vocabularies and semantic relations for translating and integrating the different sources. In this paper, we propose an integrated approach for extracting ontological structure from folksonomies that exploits the power of low support association rule mining supplemented by an upper ontology such as WordNet.}, address = {Berlin / Heidelberg}, affiliation = {The University of Sydney School of Information Technologies Australia}, author = {Lin, Huairen and Davis, Joseph and Zhou, Ying}, booktitle = {The Semantic Web: Research and Applications}, doi = {10.1007/978-3-642-02121-3_48}, editor = {Aroyo, Lora and Traverso, Paolo and Ciravegna, Fabio and Cimiano, Philipp and Heath, Tom and Hyvönen, Eero and Mizoguchi, Riichiro and Oren, Eyal and Sabou, Marta and Simperl, Elena}, file = {lin2009integrated.pdf:lin2009integrated.pdf:PDF}, groups = {public}, interhash = {562f58cbd8a8d687db0a755d58ce143c}, intrahash = {d6e768c5a4d0ac6dd667339c44607777}, pages = {654-668}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2011-02-08 04:12:15}, title = {An Integrated Approach to Extracting Ontological Structures from Folksonomies}, url = {http://dx.doi.org/10.1007/978-3-642-02121-3_48}, username = {dbenz}, volume = 5554, year = 2009 } @inproceedings{rattenbury2007towards, abstract = {We describe an approach for extracting semantics of tags, unstructured text-labels assigned to resources on the Web, based on each tag's usage patterns. In particular, we focus on the problem of extracting place and event semantics for tags that are assigned to photos on Flickr, a popular photo sharing website that supports time and location (latitude/longitude) metadata. We analyze two methods inspired by well-known burst-analysis techniques and one novel method: Scale-structure Identification. We evaluate the methods on a subset of Flickr data, and show that our Scale-structure Identification method outperforms the existing techniques. The approach and methods described in this work can be used in other domains such as geo-annotated web pages, where text terms can be extracted and associated with usage patterns.}, address = {New York, NY, USA}, author = {Rattenbury, Tye and Good, Nathaniel and Naaman, Mor}, booktitle = {SIGIR '07: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, doi = {10.1145/1277741.1277762}, file = {rattenbury2007towards.pdf:rattenbury2007towards.pdf:PDF}, groups = {public}, interhash = {8b02d2b3fdbb97c3db6e3b23079a56e5}, intrahash = {bf6f73d2ef74ca6f1d355fb5688b673c}, isbn = {978-1-59593-597-7}, pages = {103--110}, publisher = {ACM Press}, timestamp = {2010-11-10 15:35:25}, title = {Towards automatic extraction of event and place semantics from flickr tags}, url = {http://dx.doi.org/10.1145/1277741.1277762}, username = {dbenz}, year = 2007 } @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 }