@inproceedings{benz2007position, abstract = {The emergence of collaborative tagging systems with their underlying flat and uncontrolled resource organization paradigm has led to a large number of research activities focussing on a formal description and analysis of the resulting “folksonomies??. An interesting outcome is that the characteristic qualities of these systems seem to be inverse to more traditional knowledge structuring approaches like taxonomies or ontologies: The latter provide rich and precise semantics, but suffer - amongst others - from a knowledge acquisition bottleneck. An important step towards exploiting the possible synergies by bridging the gap between both paradigms is the automatic extraction of relations between tags in a folksonomy. This position paper presents preliminary results of ongoing work to induce hierarchical relationships among tags by analyzing the aggregated data of collaborative tagging systems as a basis for an ontology learning procedure.}, author = {Benz, Dominik and Hotho, Andreas}, booktitle = {Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007)}, editor = {Hinneburg, Alexander}, file = {benz2007position.pdf:benz2007position.pdf:PDF}, groups = {public}, interhash = {ff7de5717f771dabd764675279ff3adf}, intrahash = {72bff5ebe5dfb5023f62ba9b94e6ed01}, isbn = {978-3-86010-907-6}, month = sep, note = {http://lwa07.informatik.uni-halle.de/kdml07/kdml07.htm}, pages = {109--112}, publisher = {Martin-Luther-Universität Halle-Wittenberg}, title = {Position Paper: Ontology Learning from Folksonomies}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2007position.pdf}, username = {dbenz}, year = 2007 } @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{zhou2008unsupervised, abstract = {This paper deals with the problem of exploring hierarchical semantics from social annotations. Recently, social annotationservices have become more and more popular in Semantic Web. It allows users to arbitrarily annotate web resources, thus, largelylowers the barrier to cooperation. Furthermore, through providing abundant meta-data resources, social annotation might becomea key to the development of Semantic Web. However, on the other hand, social annotation has its own apparent limitations,for instance, 1) ambiguity and synonym phenomena and 2) lack of hierarchical information. In this paper, we propose an unsupervisedmodel to automatically derive hierarchical semantics from social annotations. Using a social bookmark service Del.icio.usas example, we demonstrate that the derived hierarchical semantics has the ability to compensate those shortcomings. We furtherapply our model on another data set from Flickr to testify our model’s applicability on different environments. The experimentalresults demonstrate our model’s efficiency.}, author = {Zhou, Mianwei and Bao, Shenghua and Wu, Xian and Yu, Yong}, file = {zhou2008unsupervised.pdf:zhou2008unsupervised.pdf:PDF}, groups = {public}, interhash = {e8397fd51d43531b91e81776c879f487}, intrahash = {ee6da1cc1300cf4fb68fc58d5e2bb819}, journal = {The Semantic Web}, pages = {680--693}, timestamp = {2009-09-24 23:27:32}, title = {An Unsupervised Model for Exploring Hierarchical Semantics from Social Annotations}, url = {http://dx.doi.org/10.1007/978-3-540-76298-0_49}, username = {dbenz}, year = 2008 } @incollection{cimiano2004learning, abstract = {We present a novel approach to the automatic acquisition of taxonomic relations. The main difference to earlier approaches is that we do not only consider one single source of evidence, i.e. a specific algorithm or approach, but examine the possibility of learning taxonomic relations by considering various and heterogeneous forms of evidence. In particular, we derive these different evidences by using well-known NLP techniques and resources and combine them via two simple strategies. Our approach shows very promising results compared to other results from the literature. The main aim of the work presented in this paper is (i) to gain insight into the behaviour of different approaches to learn taxonomic relations, (ii) to provide a first step towards combining these different approaches, and (iii) to establish a baseline for further research.}, author = {Cimiano, P. and Schmidt-Thieme, L. and Pivk, A. and Staab, S.}, booktitle = {Ontology Learning from Text: Methods, Applications and Evaluation}, editor = {Buitelaar, P. and Cimiano, P. and Magnini, B.}, file = {cimiano2004learning.pdf:cimiano2004learning.pdf:PDF}, groups = {public}, interhash = {456dca134a65c911721b0520a96e2352}, intrahash = {967508b78e610182ff57251eced2912d}, number = 123, pages = {59--73}, publisher = {IOS Press}, series = {Frontiers in Artificial Intelligence and Appl}, timestamp = {2011-02-02 14:21:11}, title = {Learning Taxonomic Relations from Heterogeneous Evidence}, url = {http://www.aifb.uni-karlsruhe.de/Publikationen/showPublikation_english?publ_id=746}, username = {dbenz}, year = 2004 } @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 } @inproceedings{begelman2006automated, abstract = {The use of clustering techniques enhances the user experience and thus the success of collaborative tagging services. We show that clustering techniques can improve the user experience of current tagging services. We first describe current limitations of tagging services, second, we give an overview of existing approaches. We then describe the algorithms we used for tag clustering and give experimental results and a variety of conclusions.}, address = {Edinburgh, Scotland}, author = {Begelman, Grigory and Keller, Philipp and Smadja, Frank}, booktitle = {Proceedings of the Collaborative Web Tagging Workshop at the WWW 2006}, file = {begelman2006automated.pdf:begelman2006automated.pdf:PDF}, groups = {public}, interhash = {ffacd9d40f6cba1aa8140f501c2a1802}, intrahash = {9e35d7026bdc67616cd1a01c2028644c}, lastdatemodified = {2006-10-09}, lastname = {Begelman}, month = May, own = {own}, pdf = {begelman06-automated.pdf}, read = {notread}, timestamp = {2007-09-11 13:31:19}, title = {Automated Tag Clustering: Improving search and exploration in the tag space}, url = {http://.pui.ch/phred/automated_tag_clustering/}, username = {dbenz}, year = 2006 } @inproceedings{bast2005discovering, abstract = {We show that eigenvector decomposition can be used to extract a term taxonomy from a given collection of text documents. So far, methods based on eigenvector decomposition, such as latent semantic indexing (LSI) or principal component analysis (PCA), were only known to be useful for extracting symmetric relations between terms. We give a precise mathematical criterion for distinguishing between four kinds of relations of a given pair of terms of a given collection: unrelated (car - fruit), symmetrically related (car - automobile), asymmetrically related with the first term being more specific than the second (banana - fruit), and asymmetrically related in the other direction (fruit - banana).We give theoretical evidence for the soundness of our criterion, by showing that in a simplified mathematical model the criterion does the apparently right thing. We applied our scheme to the reconstruction of a selected part of the open directory project (ODP) hierarchy, with promising results.}, author = {Bast, Holger and Dupret, Georges and Majumdar, Debapriyo and Piwowarski, Benjamin}, booktitle = {EWMF/KDO}, file = {bast2005discovering.pdf:bast2005discovering.pdf:PDF}, groups = {public}, interhash = {c5fbe42cd55b7d51e79b4e1e28909e39}, intrahash = {608e78dfe0b7e4232858673fa9111d16}, lastdatemodified = {2007-04-10}, own = {notown}, pages = {103-120}, pdf = {bast05-discovering.pdf}, read = {notread}, timestamp = {2009-09-12 14:49:11}, title = {Discovering a Term Taxonomy from Term Similarities Using Principal Component Analysis.}, username = {dbenz}, year = 2005 } @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{dupret2006principal, abstract = {We show that the singular value decomposition of a term similarity matrix induces a term hierarchy. This decomposition, usedin Latent Semantic Analysis and Principal Component Analysis for text, aims at identifying “conceptsâ€�? that can be used inplace of the terms appearing in the documents. Unlike terms, concepts are by construction uncorrelated and hence are lesssensitive to the particular vocabulary used in documents. In this work, we explore the relation between terms and conceptsand show that for each term there exists a latent subspace dimension for which the term coincides with a concept. By varyingthe number of dimensions, terms similar but more specific than the concept can be identified, leading to a term hierarchy.}, author = {Dupret, Georges and Piwowarski, Benjamin}, file = {:bast06-principal.pdf:PDF;dupret2006principal.pdf:dupret2006principal.pdf:PDF}, groups = {public}, interhash = {c1a309fb28731d35121b505f60e89ef1}, intrahash = {b1f3cfc1d060423e224db9a0b0cdbbe6}, journal = {String Processing and Information Retrieval}, journalpub = {1}, pages = {37--48}, timestamp = {2007-10-22 13:37:16}, title = {Principal Components for Automatic Term Hierarchy Building}, url = {http://dx.doi.org/10.1007/11880561_4}, username = {dbenz}, year = 2006 } @article{eda2009effectiveness, abstract = {In this paper, we evaluate the effectiveness of a semantic smoothing technique to organize folksonomy tags. Folksonomy tags have no explicit relations and vary because they form uncontrolled vocabulary. We discriminates so-called subjective tags like “cool�? and “fun�? from folksonomy tags without any extra knowledge other than folksonomy triples and use the level of tag generalization to form the objective tags into a hierarchy.We verify that entropy of folksonomy tags is an effective measure for discriminating subjective folksonomy tags. Our hierarchical tag allocation method guarantees the number of children nodes and increases the number of available paths to a target node compared to an existing tree allocation method for folksonomy tags.}, author = {Eda, Takeharu and Yoshikawa, Masatoshi and Uchiyama, Toshio and Uchiyama, Tadasu}, ee = {http://dx.doi.org/10.1007/s11280-009-0069-1}, file = {eda2009effectiveness.pdf:eda2009effectiveness.pdf:PDF}, groups = {public}, interhash = {a560796c977bc7582017f662bf88c16d}, intrahash = {ec3c256e7d1f24cd9d407d3ce7e41d96}, journal = {World Wide Web}, journalpub = {1}, number = 4, pages = {421-440}, timestamp = {2010-08-15 15:00:40}, title = {The Effectiveness of Latent Semantic Analysis for Building Up a Bottom-up Taxonomy from Folksonomy Tags.}, url = {http://dblp.uni-trier.de/db/journals/www/www12.html#EdaYUU09}, username = {dbenz}, volume = 12, year = 2009 } @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 } @incollection{haridas2009exploring, abstract = {The outgrowth of social networks in the recent years has resulted in opportunities for interesting data mining problems, such as interest or friendship recommendations. A global ontology over the interests specified by the users of a social network is essential for accurate recommendations. We propose, evaluate and compare three approaches to engineering a hierarchical ontology over user interests. The proposed approaches make use of two popular knowledge bases, Wikipedia and Directory Mozilla, to extract interest definitions and/or relationships between interests. More precisely, the first approach uses Wikipedia to find interest definitions, the latent semantic analysis technique to measure the similarity between interests based on their definitions, and an agglomerative clustering algorithm to group similar interests into higher level concepts. The second approach uses the Wikipedia Category Graph to extract relationships between interests, while the third approach uses Directory Mozilla to extract relationships between interests. Our results show that the third approach, although the simplest, is the most effective for building a hierarchy over user interests.}, address = {Berlin / Heidelberg}, affiliation = {Kansas State University Nichols Hall Manhattan KS 66502}, author = {Haridas, Mandar and Caragea, Doina}, booktitle = {On the Move to Meaningful Internet Systems: OTM 2009}, doi = {10.1007/978-3-642-05151-7_35}, editor = {Meersman, Robert and Dillon, Tharam and Herrero, Pilar}, file = {haridas2009exploring.pdf:haridas2009exploring.pdf:PDF}, groups = {public}, interhash = {2363d3cb1430a4b279692e1ff3413809}, intrahash = {982538ff1fd44d2c3296b700eac859b3}, pages = {1238-1245}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2010-10-18 15:53:06}, title = {Exploring Wikipedia and DMoz as Knowledge Bases for Engineering a User Interests Hierarchy for Social Network Applications}, url = {http://dx.doi.org/10.1007/978-3-642-05151-7_35}, username = {dbenz}, volume = 5871, year = 2009 } @techreport{heymann2006collaborative, 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.}, author = {Heymann, Paul and Garcia-Molina, Hector}, file = {heymann2006collaborative.pdf:heymann2006collaborative.pdf:PDF}, groups = {public}, institution = {Computer Science Department, Standford University}, interhash = {d77846b40aadb0e25233cabf905bb93e}, intrahash = {a6010ad0fef7cb1442298402ebb979b6}, lastdatemodified = {2007-04-27}, lastname = {Heymann}, month = {April}, own = {own}, pdf = {heyman06-collaborative.pdf}, read = {notread}, timestamp = {2007-05-25 16:05:53}, title = {Collaborative Creation of Communal Hierarchical Taxonomies in Social Tagging Systems}, url = {dbpubs.stanford.edu:8090/pub/2006-10}, username = {dbenz}, year = 2006 } @inproceedings{hjelm2008multilingual, abstract = {We present a system for taxonomy extraction, aimed at providing a taxonomic backbone in an ontology learning environment. We follow previous research in using hierarchical clustering based on distributional similarity of the terms in texts. We show that basing the clustering on a comparable corpus in four languages gives a considerable improvement in accuracy compared to using only the monolingual English texts. We also show that hierarchical k-means clustering increases the similarity to the original taxonomy, when compared with a bottom-up agglomerative clustering approach.}, author = {Hjelm, Hans and Buitelaar, Paul}, booktitle = {ECAI}, crossref = {conf/ecai/2008}, editor = {Ghallab, Malik and Spyropoulos, Constantine D. and Fakotakis, Nikos and Avouris, Nikolaos M.}, ee = {http://dx.doi.org/10.3233/978-1-58603-891-5-288}, file = {hjelm2008multilingual.pdf:hjelm2008multilingual.pdf:PDF}, groups = {public}, interhash = {21a658154fb1a02e773b7a678b15f9f4}, intrahash = {813903a333a40ecf9a59ded552acb323}, isbn = {978-1-58603-891-5}, pages = {288-292}, publisher = {IOS Press}, series = {Frontiers in Artificial Intelligence and Applications}, timestamp = {2011-01-18 12:06:01}, title = {Multilingual Evidence Improves Clustering-based Taxonomy Extraction.}, url = {http://www.ling.su.se/staff/hans/artiklar/ecai2008-hjelm-buitelaar.pdf}, username = {dbenz}, volume = 178, year = 2008 } @article{meo2009exploitation, abstract = {In this paper we present a new approach to supporting users to annotate and browse resources referred by a folksonomy. Our approach is characterized by the following novelties: (i) it proposes a probabilistic technique to quickly and accurately determine the similarity and the generalization degrees of two tags; (ii) it proposes two hierarchical structures and two related algorithms to arrange groups of semantically related tags in a hierarchy; this allows users to visualize tags of their interests according to desired semantic granularities and, then, helps them to find those tags best expressing their information needs. In this paper we first illustrate the technical characteristics of our approach; then we describe various experiments allowing its performance to be tested; finally, we compare it with other related approaches already proposed in the literature.}, address = {Oxford, UK, UK}, author = {Meo, Pasquale De and Quattrone, Giovanni and Ursino, Domenico}, doi = {http://dx.doi.org/10.1016/j.is.2009.02.004}, file = {meo2009exploitation.pdf:meo2009exploitation.pdf:PDF}, groups = {public}, interhash = {106972d128b1ec0f9d66e2edf1590d0d}, intrahash = {014f9b4d75c01fa83bfa5eb703eea2d4}, issn = {0306-4379}, journal = {Inf. Syst.}, journalpub = {1}, number = 6, pages = {511--535}, publisher = {Elsevier Science Ltd.}, timestamp = {2009-12-17 14:17:03}, title = {Exploitation of semantic relationships and hierarchical data structures to support a user in his annotation and browsing activities in folksonomies}, url = {http://portal.acm.org/citation.cfm?id=1542755}, username = {dbenz}, volume = 34, year = 2009 } @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{sanderson1999deriving, abstract = {This paper presents a means of automatically deriving a hierarchical organization of concepts from a set of documents without use of training data or standard clustering techniques. Instead, salient words and phrases extracted from the documents are organized hierarchically using a type of co-occurrence known as subsumption. The resulting structure is displayed as a series of hierarchical menus. When generated from a set of retrieved documents, a user browsing the menus is provided with a detailed overview of their content in a manner distinct from existing overview and summarization techniques. The methods used to build the structure are simple, but appear to be effective: a smallscale user study reveals that the generated hierarchy possesses properties expected of such a structure in that general terms are placed at the top levels leading to related and more specific terms below. The formation and presentation of the hierarchy is described along with the user study and some other informal evaluations.}, author = {Sanderson, Mark and Croft, William Bruce}, booktitle = {Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'99}, file = {sanderson1999deriving.pdf:sanderson1999deriving.pdf:PDF}, groups = {public}, interhash = {b351eb1a827b4d024323c4706035c938}, intrahash = {d15caaaea82b6df0747cc298a8b13556}, lastdatemodified = {2007-04-14}, lastname = {Sanderson}, own = {notown}, pages = {206--213}, pdf = {sanderson99-deriving.pdf}, read = {notread}, timestamp = {2007-09-11 13:31:34}, title = {Deriving concept hierarchies from text}, username = {dbenz}, year = 1999 } @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 } @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 }