@inproceedings{aurnhammer2006augmenting, abstract = {We propose an approach that unifies browsing by tags and visual features for intuitive exploration of image databases. Incontrast to traditional image retrieval approaches, we utilise tags provided by users on collaborative tagging sites, complementedby simple image analysis and classification. This allows us to find new relations between data elements. We introduce theconcept of a navigation map, that describes links between users, tags, and data elements for the example of the collaborativetagging site Flickr. We show that introducing similarity search based on image features yields additional links on this map.These theoretical considerations are supported by examples provided by our system, using data and tags from real Flickr users.}, author = {Aurnhammer, Melanie and Hanappe, Peter and Steels, Luc}, file = {aurnhammer2006augmenting.pdf:aurnhammer2006augmenting.pdf:PDF}, groups = {public}, interhash = {a9d35e917da138f929b5d81f1dab4fd0}, intrahash = {a286ce64106a503e135e7114365c77b2}, journal = {The Semantic Web - ISWC 2006}, pages = {58--71}, timestamp = {2009-08-11 18:38:56}, title = {Augmenting Navigation for Collaborative Tagging with Emergent Semantics}, url = {http://dx.doi.org/10.1007/11926078_5}, username = {dbenz}, volume = 4273, year = 2006 } @inproceedings{bullinaria2008semantic, author = {Bullinaria, J.A.}, file = {bullinaria2008semantic.pdf:bullinaria2008semantic.pdf:PDF}, groups = {public}, interhash = {cdb7b1ff0e89f61f84e2c15a0e46c221}, intrahash = {efae206c0f89363a3273a8d57c87eff5}, journal = {ESSLLI Workshop on Distributional Lexical Semantics}, timestamp = {2011-01-28 09:53:43}, title = {Semantic Categorization Using Simple Word Co-occurrence statistics}, username = {dbenz}, year = 2008 } @inproceedings{cantador2008enriching, abstract = {Many advanced recommendation frameworks employ ontologies of various complexities to model individuals and items, providing a mechanism for the expression of user interests and the representation of item attributes. As a result, complex matching techniques can be applied to support individuals in the discovery of items according to explicit and implicit user preferences. Recently, the rapid adoption of Web2.0, and the proliferation of social networking sites, has resulted in more and more users providing an increasing amount of information about themselves that could be exploited for recommendation purposes. However, the unification of personal information with ontologies using the contemporary knowledge representation methods often associated with Web2.0 applications, such as community tagging, is a non-trivial task. In this paper, we propose a method for the unification of tags with ontologies by grounding tags to a shared representation in the form of Wordnet and Wikipedia. We incorporate individuals’ tagging history into their ontological profiles by matching tags with ontology concepts. This approach is preliminary evaluated by extending an existing news recommendation system with user tagging histories harvested from popular social networking sites.}, author = {Cantador, Ivan and Szomszor, Martin and Alani, Harith and Fernandez, Miriam and Castells, Pablo}, booktitle = {1st International Workshop on Collective Semantics: Collective Intelligence \& the Semantic Web (CISWeb 2008) }, file = {cantador2008enriching.pdf:cantador2008enriching.pdf:PDF}, groups = {public}, interhash = {b201967f2e9ef8e8907f18fe139a306b}, intrahash = {00806894ae96282af699a8d87453d9fd}, month = {June}, timestamp = {2011-02-17 10:58:34}, title = {Enriching Ontological User Profiles with Tagging History for Multi-Domain Recommendations}, url = {http://eprints.ecs.soton.ac.uk/15451/}, username = {dbenz}, year = 2008 } @inproceedings{christiaens2006metadata, abstract = {In this paper we give a brief overview of different metadata mechanisms (like ontologies and folksonomies) and how they relate to each other. We identify major strengths and weaknesses of these mechanisms. We claim that these mechanisms can be classified from restricted (e.g., ontology) to free (e.g., free text tagging). In our view, these mechanisms should not be used in isolation, but rather as complementary solutions, in a continuous process wherein the strong points of one increase the semantic depth of the other. We give an overview of early active research already going on in this direction and propose that methodologies to support this process be developed. We demonstrate a possible approach, in which we mix tagging, taxonomy and ontology.}, author = {Christiaens, Stijn}, booktitle = {Lecture Notes in Computer Science: On the Move to Meaningful Internet Systems 2006: OTM 2006 Workshops}, file = {christiaens2006metadata.pdf:christiaens2006metadata.pdf:PDF}, groups = {public}, interhash = {f733d993459329ed1ef9f26d303ba0d9}, intrahash = {efc1396e845f3db1688dc8ef154d9520}, lastdatemodified = {2007-01-04}, lastname = {Christiaens}, own = {notown}, pdf = {christiaens06-metadata.pdf}, publisher = {Springer}, read = {notread}, timestamp = {2007-09-11 13:31:23}, title = {Metadata Mechanisms: From Ontology to Folksonomy ... and Back}, url = {http://www.springerlink.com/content/m370107220473394}, username = {dbenz}, workshoppub = {1}, year = 2006 } @inproceedings{gabrilovich2007computing, abstract = {Computing semantic relatedness of natural language texts requires access to vast amounts of common-sense and domain-specific world knowledge. We propose Explicit Semantic Analysis (ESA), a novel method that represents the meaning of texts in a high-dimensional space of concepts derived from Wikipedia. We use machine learning techniques to explicitly represent the meaning of any text as a weighted vector of Wikipedia-based concepts. Assessing the relatedness of texts in this space amounts to comparing the corresponding vectors using conventional metrics (e.g., cosine). Compared with the previous state of the art, using ESA results in substantial improvements in correlation of computed relatedness scores with human judgments: from r = 0:56 to 0:75 for individual words and from r = 0:60 to 0:72 for texts. Importantly, due to the use of natural concepts, the ESA model is easy to explain to human users.}, author = {Gabrilovich, E. and Markovitch, S.}, booktitle = {Proceedings of the 20th International Joint Conference on Artificial Intelligence}, file = {gabrilovich2007computing.pdf:gabrilovich2007computing.pdf:PDF}, groups = {public}, interhash = {5baf6af4bf58cf3926b39a12edb35e58}, intrahash = {839a06f838f02c04a8569fd41a5da284}, pages = {6--12}, timestamp = {2010-08-16 14:11:53}, title = {Computing semantic relatedness using wikipedia-based explicit semantic analysis}, url = {http://scholar.google.de/scholar.bib?q=info:woCrRNTAsA4J:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=3}, username = {dbenz}, year = 2007 } @inproceedings{garcia2009preliminary, abstract = {The availability of tag-based user-generated content for a variety of Web resources (music, photos, videos, text, etc.) has largely increased in the last years. Users can assign tags freely and then use them to share and retrieve information. However, tag-based sharing and retrieval is not optimal due to the fact that tags are plain text labels without an explicit or formal meaning, and hence polysemy and synonymy should be dealt with appropriately. To ameliorate these problems, we propose a context-based tag disambiguation algorithm that selects the meaning of a tag among a set of candidate DBpedia entries, using a common information retrieval similarity measure. The most similar DBpedia en-try is selected as the one representing the meaning of the tag. We describe and analyze some preliminary results, and discuss about current challenges in this area.}, author = {Garcia, Andres and Szomszor, Martin and Alani, Harith and Corcho, Oscar}, booktitle = {Knowledge Capture (K-Cap'09) - First International Workshop on Collective Knowledge Capturing and Representation - CKCaR'09}, file = {garcia2009preliminary.pdf:garcia2009preliminary.pdf:PDF}, groups = {public}, interhash = {5da3fa037c8f1bc0b4a6255a46e08077}, intrahash = {dfe0fee496a65763bcfae4070ffcf47e}, month = {September}, timestamp = {2011-02-17 10:59:45}, title = {Preliminary Results in Tag Disambiguation using DBpedia}, url = {http://eprints.ecs.soton.ac.uk/17792/}, 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 } @misc{hamasaki2007ontology, abstract = {This paper proposes integration of a social network with the tripartite model of ontologies by P. Mika. That model is based on three dimensions, i.e. actors, concepts and instances, and illustrates ontology emergence using actor-concept and conceptinstance relations. However, another important ingredient is the actor-actor relation. For example, a vocabulary is sometimes shared within a community, which consists of dense relations among persons. Through considering of who knows whom (as described in FOAF) and who collaborates with whom, the extracted ontology might be improved. We propose an advanced model based on Mika’s work, and describe a case study using the model. We show an application of an extracted ontology for information recommendation for academic conferences.}, author = {Hamasaki, Masahiro and Matsuo, Yutaka and Nisimura, T.}, booktitle = {International Workshop on Semantic Web for Collaborative Knowledge Acquisition (SWECKA2007)}, file = {hamasaki2007ontology.pdf:hamasaki2007ontology.pdf:PDF}, groups = {public}, interhash = {4a452a28251de436b241f42ee3ac9c32}, intrahash = {fad2913a06c8cb158a69a80e3dcbdecd}, timestamp = {2011-02-17 11:03:58}, title = {Ontology Extraction using Social Network}, url = {http://staff.aist.go.jp/masahiro.hamasaki/index-e.html}, username = {dbenz}, year = 2007 } @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{kennedy2007how, abstract = {The advent of media-sharing sites like Flickr and YouTube has drastically increased the volume of community-contributed multimedia resources available on the web. These collections have a previously unimagined depth and breadth, and have generated new opportunities – and new challenges – to multimedia research. How do we analyze, understand and extract patterns from these new collections? How can we use these unstructured, unrestricted community contributions of media (and annotation) to generate “knowledge�?? As a test case, we study Flickr – a popular photo sharing website. Flickr supports photo, time and location metadata, as well as a light-weight annotation model. We extract information from this dataset using two different approaches. First, we employ a location-driven approach to generate aggregate knowledge in the form of “representative tags�? for arbitrary areas in the world. Second, we use a tag-driven approach to automatically extract place and event semantics for Flickr tags, based on each tag’s metadata patterns. With the patterns we extract from tags and metadata, vision algorithms can be employed with greater precision. In particular, we demonstrate a location-tag-vision-based approach to retrieving images of geography-related landmarks and features from the Flickr dataset. The results suggest that community-contributed media and annotation can enhance and improve our access to multimedia resources – and our understanding of the world.}, address = {New York, NY, USA}, author = {Kennedy, Lyndon and Naaman, Mor and Ahern, Shane and Nair, Rahul and Rattenbury, Tye}, booktitle = {MULTIMEDIA '07: Proceedings of the 15th international conference on Multimedia}, citeulike-article-id = {2626639}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1291384}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1291233.1291384}, doi = {10.1145/1291233.1291384}, file = {kennedy2007how.pdf:kennedy2007how.pdf:PDF}, groups = {public}, interhash = {cd4acdd5a627c20e9effdbda54dd122d}, intrahash = {7069480c43ba5d41396e075307cd1af1}, isbn = {9781595937025}, pages = {631--640}, posted-at = {2009-06-25 14:41:53}, priority = {2}, publisher = {ACM}, timestamp = {2011-02-17 11:07:22}, title = {How flickr helps us make sense of the world: context and content in community-contributed media collections}, url = {http://dx.doi.org/10.1145/1291233.1291384}, username = {dbenz}, year = 2007 } @inproceedings{lee2007tagplus, abstract = {Collaborative tagging describes the process by which many users add metadata in the form of keywords to shared content. Recently, collaborative tagging has grown in popularity on the web, on sites that allow users to tag bookmarks, photographs, videos and other content. In ubiquitous computing environment, users access data through various kinds of mobile terminals. Therefore users want more accurate materials because of expensive communication cost or the useless results due to abuse of tags. In this paper, we first describe current limitation of tagging services. We then describe the system (TagPlus) we implemented to minimize ambiguity due to no synonym control. Finally, we give experimental results.}, acmid = {1262879}, address = {Washington, DC, USA}, author = {Lee, Sun-Sook and Yong, Hwan-Seung}, booktitle = {Proceedings of the 2007 International Conference on Multimedia and Ubiquitous Engineering}, doi = {http://dx.doi.org/10.1109/MUE.2007.201}, groups = {public}, interhash = {c7483ed06e2da8caa622186b464233c7}, intrahash = {4344c37b828436f882b45f0f750ce1c4}, isbn = {0-7695-2777-9}, numpages = {5}, pages = {294--298}, publisher = {IEEE Computer Society}, series = {MUE '07}, timestamp = {2011-02-17 11:08:54}, title = {TagPlus: A Retrieval System using Synonym Tag in Folksonomy}, url = {http://dx.doi.org/10.1109/MUE.2007.201}, username = {dbenz}, year = 2007 } @article{maala2008conversion, abstract = {The recent evolution of the Web, now designated by the term Web 2.0, has seen the appearance of a huge number of resources created and annotated by users. However the annotations consist only in simple tags that are gathered in unstructured sets called folksonomies. The use of more complex languages to annotate resources and to define semantics according to the vision of the Semantic Web, would improve the understanding by machines and programs, like search engines, of what is on the Web. Indeed tags expressivity is very low compared to the representation standards of the Semantic Web, like RDF and OWL. But users appear to be still reluctant to annotate resources with RDF, and it should be recognized that Semantic Web, contrary to Web 2.0, is still not a reality of today’s Web. One way to take advantage of Semantic Web capabilities right now, without waiting for a change of the annotation usages, would be to be able to generate RDF annotations from tags. As a first step toward this direction, this paper presents a tentative to automatically convert a set of tags into a RDF description in the context of photos on Flickr. Such a method exploits some specificity of tags used on Flickr, some basic natural language processing tools and some semantic resources, in order to relate semantically tags describing a given photo and build a pertinent RDF annotation for this photo.}, author = {{Maala}, Mohamed Zied and {Delteil}, Alexandre and {Azough}, Ahmed}, file = {maala2008conversion.pdf:maala2008conversion.pdf:PDF}, groups = {public}, interhash = {5c33bd9a53959a0b6a98b0c531ec5fb3}, intrahash = {28bce2838aabcc24839eb9b64cc92f50}, issn = {1645-7641}, journal = {IADIS INTERNATIONAL JOURNAL ON WWW/INTERNET}, language = {en}, number = 1, timestamp = {2011-02-17 11:12:11}, title = {{A conversion process from Flickr tags to RDF descriptions}}, url = {http://liris.cnrs.fr/publis/?id=4425}, username = {dbenz}, volume = 6, year = 2008 } @inproceedings{medelyan2008integrating, abstract = {Integration of ontologies begins with establishing mappings between their concept entries. We map categories from the largest manually-built ontology, Cyc, onto Wikipedia articles describing corresponding concepts. Our method draws both on Wikipedia’s rich but chaotic hyperlink structure and Cyc’s carefully defined taxonomic and common-sense knowledge. On 9,333 manual alignments by one person, we achieve an F-measure of 90%; on 100 alignments by six human subjects the average agreement of the method with the subject is close to their agreement with each other. We cover 62.8% of Cyc categories relating to common-sense knowledge and discuss what further information might be added to Cyc given this substantial new alignment.}, author = {Medelyan, O. and Legg, C.}, booktitle = {Proceedings of the WIKI-AI: Wikipedia and AI Workshop at the AAAI}, file = {medelyan2008integrating.pdf:medelyan2008integrating.pdf:PDF}, groups = {public}, interhash = {c279a921a5ac878ca952a4683ce9ac7a}, intrahash = {245629fc15b53a08a24df90f086e7b25}, timestamp = {2010-11-10 11:57:58}, title = {Integrating Cyc and Wikipedia: Folksonomy meets rigorously defined common-sense}, url = {http://scholar.google.de/scholar.bib?q=info:hgFpsjJR__4J:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=58}, username = {dbenz}, volume = 8, year = 2008 } @inproceedings{passant2007using, abstract = {While free-tagging classification is widely used in social software implementations and especially in weblogs, it raises various issues regarding information retrieval. In this paper, we describe an approach that mixes folksonomies and semantic web technologies in order to solve some of these problems, and to enrich information retrieval capabilities among blog posts.We first introduce the corporate context of the study and the issues we have faced that motivated our approach. Then, we argue how the use of domain ontologies combined with the SIOC vocabulary on the top of an existing folksonomy and weblogging platform offers a way to get rid of free-tagging classification flaws, and enhances information retrieval by suggesting related blog posts.Aside of the theoretical background, this paper also focuses on implementation. We present experimental results of this approach through the example of add-ons to a corporate blogging platform and the associated semantic web search engine, that extensively uses RDF and other semantic web technologies to find appropriate information and suggest related posts.}, address = {Boulder, Colorado}, author = {Passant, Alexandre}, booktitle = {Proceedings of the First International Conference on Weblogs and Social Media (ICWSM)}, file = {passant2007using.pdf:passant2007using.pdf:PDF}, groups = {public}, interhash = {4a44286e417cf21aab89123e8bc6d51a}, intrahash = {b184134a9060ddedb38102bb12556314}, month = {March}, timestamp = {2011-02-17 11:21:55}, title = {{Using Ontologies to Strengthen Folksonomies and Enrich Information Retrieval in Weblogs}}, url = {http://www.icwsm.org/papers/paper15.html}, username = {dbenz}, year = 2007 } @article{passant2008meaning, abstract = {This paper introduces MOAT, a lightweight Semantic Web framework that provides a collaborative way to let Web 2.0 content producers give meanings to their tags in a machinereadable way. To achieve this goal, this approach relies on Linked Data principles, using URIs from existing resources to define these meanings. That way, users can create interlinked RDF data and let their content enter the Semantic Web, while solving some limits of free-tagging at the same time.}, author = {Passant, A. and Laublet, P.}, citeulike-article-id = {3172586}, file = {passant2008meaning.pdf:passant2008meaning.pdf:PDF}, groups = {public}, interhash = {c6ef7c21e091847e34368730e29a6b94}, intrahash = {9aa3eaabb7327971abeb82ac0d7a348d}, journal = {Proceedings of the WWW 2008 Workshop Linked Data on the Web (LDOW2008), Beijing, China, Apr}, posted-at = {2009-03-31 00:02:34}, priority = {4}, timestamp = {2011-02-17 11:22:45}, title = {Meaning Of A Tag: A collaborative approach to bridge the gap between tagging and Linked Data}, url = {http://ftp.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-369/paper22.pdf}, username = {dbenz}, year = 2008 } @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 } @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 } @article{raysonecember2008from, abstract = {This paper reports the extension of the key words method for the comparison of corpora. Using automatic tagging software that assigns part-of-speech and semantic field (domain) tags, a method is described which permits the extraction of key domains by applying the keyness calculation to tag frequency lists. The combination of the key words and key domains methods is shown to allow macroscopic analysis (the study of the characteristics of whole texts or varieties of language) to inform the microscopic level (focussing on the use of a particular linguistic feature) and thereby suggesting those linguistic features which should be investigated further. The resulting 'data-driven' approach presented here combines elements of both the 'corpus-based' and 'corpus-driven' paradigms in corpus linguistics. A web-based tool, Wmatrix, implementing the proposed method is applied in a case study: the comparison of UK 2001 general election manifestos of the Labour and Liberal Democratic parties.}, author = {Rayson, Paul}, doi = {10.1075/ijcl.13.4.06ray}, groups = {public}, interhash = {dff324bd5ca64c55a2e491e439a7b5c8}, intrahash = {753a948e9239f56f7d29b1d24bebb2a9}, journal = {International Journal of Corpus Linguistics}, journalpub = {1}, pages = {519-549(31)}, title = {From key words to key semantic domains}, url = {http://www.ingentaconnect.com/content/jbp/ijcl/2008/00000013/00000004/art00005}, username = {dbenz}, volume = 13, year = 2008 } @article{garciasilva2011review, abstract = {This paper describes and compares the most relevant approaches for associating tags with semantics in order to make explicit the meaning of those tags. We identify a common set of steps that are usually considered across all these approaches and frame our descriptions according to them, providing a unified view of how each approach tackles the different problems that appear during the semantic association process. Furthermore, we provide some recommendations on (a) how and when to use each of the approaches according to the characteristics of the data source, and (b) how to improve results by leveraging the strengths of the different approaches.}, author = {Garcia-Silva, Andres and Corcho, Oscar and Alani, Harith and Gomez-Perez, Asuncion}, file = {garciasilva2011review.pdf:garciasilva2011review.pdf:PDF}, groups = {public}, interhash = {ef913839d8ab1f3955a9d05c5ba2fadf}, intrahash = {42f77eb846bdae1847ea70ca5ba6c9ec}, journal = {Knowledge Engineering Review}, month = {December}, number = 4, timestamp = {2011-02-15 03:13:28}, title = {Review of the state of the art: Discovering and Associating Semantics to Tags in Folksonomies}, username = {dbenz}, volume = 26, year = 2011 } @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 }