@inproceedings{benz2010semantics, address = {Raleigh, NC, USA}, author = {Benz, Dominik and Hotho, Andreas and Stützer, Stefan and Stumme, Gerd}, booktitle = {Proceedings of the 2nd Web Science Conference (WebSci10)}, file = {benz2010semantics.pdf:benz2010semantics.pdf:PDF}, interhash = {d4a2f14bb27ce220ba43f651e42aeddc}, intrahash = {16c77e486fb8bc527eb7734b153932ab}, title = {Semantics made by you and me: Self-emerging ontologies can capture the diversity of shared knowledge}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010semantics.pdf}, year = 2010 } @inproceedings{bade2008evaluation, abstract = {Several learning tasks comprise hierarchies. Comparison with a "goldstandard" is often performed to evaluate the quality of a learned hierarchy. We assembled various similarity metrics that have been proposed in different disciplines and compared them in a unified interdisciplinary framework for hierarchical evaluation which is based on the distinction of three fundamental dimensions. Identifying deficiencies for measuring structural similarity, we suggest three new measures for this purpose, either extending existing ones or based on new ideas. Experiments with an artificial dataset were performed to compare the different measures. As shown by our results, the measures vary greatly in their properties.}, address = {Berlin-Heidelberg}, author = {Bade, Korinna and Benz, Dominik}, booktitle = {Proceedings of the 32nd Annual Conference of the German Classification Society - Advances in Data Analysis, Data Handling and Business Intelligence (GfKl 2008)}, file = {bade2008evaluation.pdf:bade2008evaluation.pdf:PDF}, groups = {public}, interhash = {8bb09e3197d01f7c23481c2cd68533af}, intrahash = {ec033805bc90ab87c99860e29f0d00dd}, note = {in press}, publisher = {Springer}, series = {Studies in Classification, Data Analysis, and Knowledge Organization}, title = {Evaluation Strategies for Learning Algorithms of Hierarchical Structures}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/bade2008evaluation.pdf}, username = {dbenz}, year = 2008 } @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{benz2008analyzing, abstract = {The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance.}, author = {Benz, Dominik and Grobelnik, Marko and Hotho, Andreas and Jäschke, Robert and Mladenic, Dunja and Servedio, Vito D. P. and Sizov, Sergej and Szomszor, Martin}, booktitle = {Proceedings of the Dagstuhl Seminar on Social Web Communities}, editor = {Alani, Harith and Staab, Steffen and Stumme, Gerd}, file = {benz2008analyzing.pdf:benz2008analyzing.pdf:PDF}, groups = {public}, interhash = {d738d9d90c1c466ee0a73ac0cc3dc4c1}, intrahash = {6918e578527dec96abb5718f105d9f78}, issn = {1862-4405}, number = 08391, title = {Analyzing Tag Semantics Across Collaborative Tagging Systems}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2008analyzing.pdf}, username = {dbenz}, year = 2008 } @inproceedings{benz2009characterizing, address = {Bled, Slovenia}, author = {Benz, Dominik and Krause, Beate and Kumar, G. Praveen and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the 1st Workshop on Explorative Analytics of Information Networks (EIN2009)}, file = {benz2009characterizing.pdf:benz2009characterizing.pdf:PDF}, groups = {public}, interhash = {de5e58b26200e44112d9791f39e7523d}, intrahash = {b697a98a7340585594455ee2e81d238a}, month = {September}, title = {Characterizing Semantic Relatedness of Search Query Terms}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2009characterizing.pdf}, username = {dbenz}, year = 2009 } @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{hotho2006emergent, abstract = {Social bookmark tools are rapidly emerging on the Web. In suchsystems users are setting up lightweight conceptual structurescalled folksonomies. The reason for their immediate success is thefact that no specific skills are needed for participating. In thispaper we specify a formal model for folksonomies, briefly describeour own system BibSonomy, which allows for sharing both bookmarks andpublication references, and discuss first steps towards emergent semantics.}, address = {Bonn}, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, booktitle = {Informatik 2006 -- Informatik für Menschen. Band 2}, editor = {Hochberger, Christian and Liskowsky, Rüdiger}, file = {hotho2006emergent.pdf:hotho2006emergent.pdf:PDF}, groups = {public}, interhash = {53e5677ab0bf1a8f5a635cc32c9082ba}, intrahash = {05043cc20f1e0f5a612135c970e4f1ac}, month = {October}, note = {Proc. Workshop on Applications of Semantic Technologies, Informatik 2006}, publisher = {Gesellschaft für Informatik}, series = {Lecture Notes in Informatics}, title = {Emergent Semantics in BibSonomy}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006emergent.pdf}, username = {dbenz}, volume = {P-94}, year = 2006 } @inproceedings{koerner2010stop, abstract = {Recent research provides evidence for the presence of emergent semantics in collaborative tagging systems. While several methods have been proposed, little is known about the factors that influence the evolution of semantic structures in these systems. A natural hypothesis is that the quality of the emergent semantics depends on the pragmatics of tagging: Users with certain usage patterns might contribute more to the resulting semantics than others. In this work, we propose several measures which enable a pragmatic differentiation of taggers by their degree of contribution to emerging semantic structures. We distinguish between categorizers, who typically use a small set of tags as a replacement for hierarchical classification schemes, and describers, who are annotating resources with a wealth of freely associated, descriptive keywords. To study our hypothesis, we apply semantic similarity measures to 64 different partitions of a real-world and large-scale folksonomy containing different ratios of categorizers and describers. Our results not only show that ‘verbose’ taggers are most useful for the emergence of tag semantics, but also that a subset containing only 40% of the most ‘verbose’ taggers can produce results that match and even outperform the semantic precision obtained from the whole dataset. Moreover, the results suggest that there exists a causal link between the pragmatics of tagging and resulting emergent semantics. This work is relevant for designers and analysts of tagging systems interested (i) in fostering the semantic development of their platforms, (ii) in identifying users introducing “semantic noise??, and (iii) in learning ontologies.}, address = {Raleigh, NC, USA}, author = {Körner, Christian and Benz, Dominik and Strohmaier, Markus and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the 19th International World Wide Web Conference (WWW 2010)}, file = {koerner2010stop.pdf:koerner2010stop.pdf:PDF}, groups = {public}, interhash = {5afe6e4ce8357d8ac9698060fb438468}, intrahash = {45f8d8f2a8251a5e988c596a5ebb3f2d}, month = apr, publisher = {ACM}, title = {Stop Thinking, start Tagging - Tag Semantics emerge from Collaborative Verbosity}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/koerner2010stop.pdf}, username = {dbenz}, year = 2010 } @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 } @article{levy2008learning, author = {Levy, M. and Sandler, M.}, file = {levy2008learning.pdf:levy2008learning.pdf:PDF}, groups = {public}, interhash = {82ca1eaa0983bf17582b4b02597f2a1d}, intrahash = {0681ab4879e2378295f724eb73e7360c}, journal = {Journal of New Music Research}, number = 2, pages = {137--150}, publisher = {Routledge, part of the Taylor \& Francis Group}, title = {Learning latent semantic models for music from social tags}, username = {dbenz}, volume = 37, year = 2008 } @book{manning1999foundations, address = {Cambridge, MA}, author = {Manning, C. and Sch\"utze, H.}, interhash = {a81df02f92f266a51183fe936f588a08}, intrahash = {e2f05fae5d02f579a85a10b79edf1d99}, publisher = {MIT Press}, title = {Foundations of statistical natural language processing}, year = 1999 } @inproceedings{tatu2010inducing, author = {Tatu, Marta and Moldovan, Dan I.}, booktitle = {LREC}, crossref = {conf/lrec/2010}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, ee = {http://www.lrec-conf.org/proceedings/lrec2010/summaries/203.html}, interhash = {df87cca39d1fbe9d12d5441e0be169c5}, intrahash = {deb8d2f57af4373047bcaba2fe67e39e}, isbn = {2-9517408-6-7}, publisher = {European Language Resources Association}, title = {Inducing Ontologies from Folksonomies using Natural Language Understanding.}, url = {http://dblp.uni-trier.de/db/conf/lrec/lrec2010.html#TatuM10}, year = 2010 } @mastersthesis{meder2010multidomain, author = {Meder, Michael}, groups = {public}, interhash = {c344c636c94156ba014c020d9e16b1e5}, intrahash = {7ef2f23103d4c0ed0ad344f9ead8db9d}, school = {Technische Universität Berlin}, timestamp = {2011.07.20}, title = {Multi-Domain Klassifikation basierend auf nutzergenerierten Metadaten}, username = {dbenz}, year = 2010 } @incollection{doush2010integrating, affiliation = {Yarmouk University Dept. Computer Science}, author = {Doush, Iyad Abu and Pontelli, Enrico}, booktitle = {Computers Helping People with Special Needs}, editor = {Miesenberger, Klaus and Klaus, Joachim and Zagler, Wolfgang and Karshmer, Arthur}, interhash = {e05135c7b60b2cfae3165bcf8ff9d1c7}, intrahash = {85c2161e2e6a320699e6fd71bf15393a}, note = {10.1007/978-3-642-14097-6_60}, pages = {376-383}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, title = {Integrating Semantic Web and Folksonomies to Improve E-Learning Accessibility}, url = {http://dx.doi.org/10.1007/978-3-642-14097-6_60}, volume = 6179, year = 2010 } @inproceedings{barla2009deriving, author = {Barla, Michal and Bielikov�, M�ria}, booktitle = {Computational Collective Intelligence. Semantic Web, Social Networks and Multiagent System}, editor = {Nguyen, Ngoc Thanh and Kowalczyk, Ryszard and Chen, Shyi-Ming}, interhash = {ff65905d1c79503920fa46c013c2861c}, intrahash = {98c5b4c0cdbc9344773f9867f90a6a3a}, isbn = {978-3-642-04440-3}, pages = {309-320}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {On Deriving Tagsonomies: Keyword Relations Coming from Crowd.}, url = {http://dx.doi.org/10.1007/978-3-642-04441-0_27}, volume = 5796, year = 2009 } @article{dbpedia_jws_09, author = {Lehmann, Jens and Bizer, Chris and Kobilarov, Georgi and Auer, Sören and Becker, Christian and Cyganiak, Richard and Hellmann, Sebastian}, doi = {doi:10.1016/j.websem.2009.07.002}, interhash = {087f766f30469cbc881c83ad156a104a}, intrahash = {f40d3f49ec12638400bdb99a930b4bbc}, journal = {Journal of Web Semantics}, number = 3, pages = {154--165}, title = {{DB}pedia - A Crystallization Point for the Web of Data}, url = {http://jens-lehmann.org/files/2009/dbpedia_jws.pdf}, volume = 7, year = 2009 } @article{weichselbraun2010augmenting, address = {Los Alamitos, CA, USA}, author = {Weichselbraun, Albert and Wohlgenannt, Gerhard and Scharl, Arno}, doi = {10.1109/DEXA.2010.53}, interhash = {c7adb30f1c3e4ba155dd36f76149f0eb}, intrahash = {8e2afcb17621138bf6fac716bbbd5df3}, issn = {1529-4188}, journal = {Database and Expert Systems Applications, International Workshop on}, pages = {193-197}, publisher = {IEEE Computer Society}, title = {Augmenting Lightweight Domain Ontologies with Social Evidence Sources}, url = {http://www.computer.org/portal/web/csdl/doi/10.1109/DEXA.2010.53}, volume = 0, year = 2010 } @incollection{springerlink:10.1007/978-3-540-76298-0_79, abstract = {The use of tags to describe Web resources in a collaborative manner has experienced rising popularity among Web users in recent years. The product of such activity is given the name folksonomy, which can be considered as a scheme of organizing information in the users’ own way. This research work attempts to analyze tripartite graphs – graphs involving users, tags and resources – of folksonomies and discuss how these elements acquire their semantics through their associations with other elements, a process we call mutual contextualization. By studying such process, we try to identify solutions to problems such as tag disambiguation, retrieving documents of similar topics and discovering communities of users. This paper describes the basis of the research work, mentions work done so far and outlines future plans.}, address = {Berlin / Heidelberg}, affiliation = {Intelligence, Agents and Multimedia Group (IAM), School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ UK}, author = {man Yeung, Ching and Gibbins, Nicholas and Shadbolt, Nigel}, booktitle = {The Semantic Web}, doi = {10.1007/978-3-540-76298-0_79}, editor = {Aberer, Karl and Choi, Key-Sun and Noy, Natasha and Allemang, Dean and Lee, Kyung-Il and Nixon, Lyndon and Golbeck, Jennifer and Mika, Peter and Maynard, Diana and Mizoguchi, Riichiro and Schreiber, Guus and Cudré-Mauroux, Philippe}, interhash = {739050b87c491e82396f3ad3aa87073e}, intrahash = {ceaf5504144fb6a88ef91853421a7644}, pages = {966-970}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Mutual Contextualization in Tripartite Graphs of Folksonomies}, url = {http://dx.doi.org/10.1007/978-3-540-76298-0_79}, volume = 4825, year = 2007 } @inproceedings{angeletou2008semantically, abstract = {Abstract. While the increasing popularity of folksonomies has lead to a vast quantity of tagged data, resource retrieval in folksonomies is limited by being agnostic to the meaning (i.e., semantics) of tags. Our goal is to automatically enrich folksonomy tags (and implicitly the related resources) with formal semantics by associating them to relevant concepts defined in online ontologies. We introduce FLOR, a method that performs automatic folksonomy enrichment by combining knowledge from WordNet and online available ontologies. Experimentally testing FLOR, we found that it correctly enriched 72 % of 250 Flickr photos. 1}, author = {Angeletou, Sofia and Sabou, Marta and Motta, Enrico}, booktitle = {Proceedings of the CISWeb Workshop, located at the 5th European Semantic Web Conference ESWC 2008}, file = {angeletou2008semantically.pdf:angeletou2008semantically.pdf:PDF}, groups = {public}, institution = {CiteSeerX - Scientific Literature Digital Library and Search Engine [http://citeseerx.ist.psu.edu/oai2] (United States)}, interhash = {1b244d0220730e994822192f6e1cba76}, intrahash = {e6404fa071680b21905ef7f3255359f7}, location = {http://www.scientificcommons.org/47680629}, timestamp = {2011-02-17 10:55:55}, title = {Semantically enriching folksonomies with FLOR}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.2569}, username = {dbenz}, year = 2008 } @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 } @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{tesconi2008semantify, abstract = {At present tagging is experimenting a great diffusion as the most adopted way to collaboratively classify resources over the Web. In this paper, after a detailed analysis of the attempts made to improve the organization and structure of tagging systems as well as the usefulness of this kind of social data, we propose and evaluate the Tag Disambiguation Algorithm, mining del.icio.us data. It allows to easily semantify the tags of the users of a tagging service: it automatically finds out for each tag the related concept of Wikipedia in order to describe Web resources through senses. On the basis of a set of evaluation tests, we analyze all the advantages of our sense-based way of tagging, proposing new methods to keep the set of users tags more consistent or to classify the tagged resources on the basis of Wikipedia categories, YAGO classes or Wordnet synsets. We discuss also how our semanitified social tagging data are strongly linked to DBPedia and the datasets of the Linked Data community. 1}, author = {Tesconi, Maurizio and Ronzano, Francesco and Marchetti, Andrea and Minutoli, Salvatore}, booktitle = {Proceedings of the Workshop Social Data on the Web (SDoW2008)}, crossref = {CEUR-WS.org/Vol-405}, file = {tesconi2008semantify.pdf:tesconi2008semantify.pdf:PDF}, groups = {public}, interhash = {0c1c96b41a0af8512c20a7d41504640f}, intrahash = {dd698b5ee4d93496d11627cbe1615514}, timestamp = {2009-09-27 15:57:13}, title = {Semantify del.icio.us: Automatically Turn your Tags into Senses}, url = {http://CEUR-WS.org/Vol-405/paper8.pdf}, username = {dbenz}, year = 2008 } @inproceedings{benz2010semantics, address = {Raleigh, NC, USA}, author = {Benz, Dominik and Hotho, Andreas and Stützer, Stefan and Stumme, Gerd}, booktitle = {Proceedings of the 2nd Web Science Conference (WebSci10)}, file = {benz2010semantics.pdf:benz2010semantics.pdf:PDF}, interhash = {d4a2f14bb27ce220ba43f651e42aeddc}, intrahash = {16c77e486fb8bc527eb7734b153932ab}, title = {Semantics made by you and me: Self-emerging ontologies can capture the diversity of shared knowledge}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010semantics.pdf}, year = 2010 } @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 } @misc{asur2010predicting, abstract = {In recent years, social media has become ubiquitous and important for socialnetworking and content sharing. And yet, the content that is generated fromthese websites remains largely untapped. In this paper, we demonstrate howsocial media content can be used to predict real-world outcomes. In particular,we use the chatter from Twitter.com to forecast box-office revenues for movies.We show that a simple model built from the rate at which tweets are createdabout particular topics can outperform market-based predictors. We furtherdemonstrate how sentiments extracted from Twitter can be further utilized toimprove the forecasting power of social media.}, author = {Asur, Sitaram and Huberman, Bernardo A.}, file = {asur2010predicting.pdf:asur2010predicting.pdf:PDF}, groups = {public}, interhash = {538607d6d5da7946a0c5a2114a7c44f5}, intrahash = {9c23c0465529a60d9540ee29e74856f1}, note = {cite arxiv:1003.5699}, timestamp = {2010-11-09 10:12:57}, title = {Predicting the Future with Social Media}, url = {http://arxiv.org/abs/1003.5699}, username = {dbenz}, year = 2010 } @inproceedings{heymann2010tagging, abstract = {A fundamental premise of tagging systems is that regular users can organize large collections for browsing and other tasks using uncontrolled vocabularies. Until now, that premise has remained relatively unexamined. Using library data, we test the tagging approach to organizing a collection. We find that tagging systems have three major large scale organizational features: consistency, quality, and completeness. In addition to testing these features, we present results suggesting that users produce tags similar to the topics designed by experts, that paid tagging can effectively supplement tags in a tagging system, and that information integration may be possible across tagging systems.}, author = {Heymann, Paul and Paepcke, Andreas and Garcia-Molina, Hector}, booktitle = {WSDM}, crossref = {conf/wsdm/2010}, date = {2010-02-18}, editor = {Davison, Brian D. and Suel, Torsten and Craswell, Nick and Liu, Bing}, ee = {http://doi.acm.org/10.1145/1718487.1718495}, file = {:heyman2010tagging.pdf:PDF}, groups = {public}, interhash = {d4f72ed57e6b99dbe32e18e218d81ef5}, intrahash = {12579231cd5449f9a40cba9924975f09}, isbn = {978-1-60558-889-6}, pages = {51-60}, publisher = {ACM}, timestamp = {2010-04-08 07:27:02}, title = {Tagging human knowledge.}, url = {http://dblp.uni-trier.de/db/conf/wsdm/wsdm2010.html#HeymannPG10}, username = {dbenz}, year = 2010 } @article{xia2009ballot, abstract = {The participation of individual users in online communities is one of the most noted features in the recent explosive growth of popular online communities ranging from picture and video sharing (Flickr.com and YouTube.com) and collective music recommendation (Last.fm) to news voting (Digg. com) and social bookmarking (del.icio.us). Unlike traditional online communities, these sites feature little message exchange among users. Nevertheless, users' involvement and their contribution through non-message-based interactions have become a major force behind successful online communities. Recognition of this new type of user participation is crucial to understanding the dynamics of online social communities and community monetization. The new communication features in online communities can be best summarized as Ballot Box Communication (BBC), which is an aggregation mechanism that reflects the common experience and opinions among individuals. By offering a limited number of choices such as voting, rating and tagging, BBC creates a new medium to effectively reveal the interests of mass population (see Table 1). Compared with traditional Computer Mediated Communication (CMC) such as email, Web publishing, and online forums, BBC influences user preferences by simplifying the mass sharing of individual preferences.}, address = {New York, NY, USA}, author = {Xia, Mu and Huang, Yun and Duan, Wenjing and Whinston, Andrew B.}, doi = {http://doi.acm.org/10.1145/1562164.1562199}, interhash = {020590b4b639509c89588bbcd165e51d}, intrahash = {a446ff517cf312df9cf5f6a6e45f3462}, issn = {0001-0782}, journal = {Commun. ACM}, number = 9, pages = {138--142}, publisher = {ACM}, title = {Ballot box communication in online communities}, url = {http://portal.acm.org/citation.cfm?id=1562164.1562199}, volume = 52, year = 2009 } @inproceedings{michlmayr2005case, abstract = {This paper delivers a case study on the properties of meta- data provided by a folksonomy. We provide the background about folk- sonomies and discuss to which extend the process of creating meta-data in a folksonomy is related to the idea of emergent semantics as defined by the IFIP 2.6 Working Group on Data Semantics. We conduct exper- iments to analyse the meta-data provided by the del.icio.us folksonomy and to develop a method for selecting subsets of meta-data that adhere to the principle of interest-based locality, which was originally observed in peer-to-peer environments. In addition, we compare data provided by del.icio.us to data provided by the DMOZ taxonomy.}, author = {Michlmayr, Elke}, booktitle = {Proceedings of the Workshop on Social Network Analysis, International Semantic Web Conference (ISWC)}, file = {:michlmayr05-emergent.pdf:PDF}, groups = {public}, interhash = {9aa76dc961b982569554554fa3ef5de9}, intrahash = {8799bc711fb192a577791a5fdea805f0}, lastdatemodified = {2007-04-27}, lastname = {Michlmayr}, month = {November}, own = {notown}, pdf = {michlmayr05-emergent.pdf}, read = {notread}, timestamp = {2009-11-11 16:55:59}, title = {A Case Study on Emergent Semantics in Communities}, url = {http://wit.tuwien.ac.at/people/michlmayr/index.html}, username = {dbenz}, year = 2005 } @inproceedings{veres2006language, abstract = {Folksonomies are classification schemes that emerge from the collective actions of users who tag resources with an unrestricted set of key terms. There has been a flurry of activity in this domain recently with a number of high profile web sites and search engines adopting the practice. They have sparked a great deal of excitement and debate in the popular and technical literature, accompanied by a number of analyses of the statistical properties of tagging behavior. However, none has addressed the deep nature of folksonomies. What is the nature of a tag? Where does it come from? How is it related to a resource? In this paper we present a study in which the linguistic properties of folksonomies reveal them to contain, on the one hand, tags that are similar to standard categories in taxonomies. But on the other hand, they contain additional tags to describe class properties. The implications of the findings for the relationship between folksonomy and ontology are discussed.}, address = {Berlin / Heidelberg}, author = {Veres, Csaba}, booktitle = {Natural Language Processing and Information Systems}, file = {veres2006language.pdf:veres2006language.pdf:PDF}, groups = {public}, interhash = {1787dec43f3c11153fc9d2617af8829c}, intrahash = {617763caa416f98b398cd2b2f71338ee}, lastdatemodified = {2006-09-30}, lastname = {Veres}, month = {July}, own = {notown}, pages = {58-69}, pdf = {veres06-language.pdf}, publisher = {Springer}, read = {notread}, series = {Lecture Notes in Computer Science}, timestamp = {2007-09-11 13:31:39}, title = {The Language of Folksonomies: What Tags Reveal About User Classification.}, url = {http://dx.doi.org/10.1007/11765448_6}, username = {dbenz}, volume = {3999/2006}, year = 2006 }