@inproceedings{alkhalifa2007towards, acmid = {1286288}, address = {New York, NY, USA}, author = {Al-Khalifa, Hend S. and Davis, Hugh C.}, booktitle = {Proceedings of the eighteenth conference on Hypertext and hypermedia}, doi = {http://doi.acm.org/10.1145/1286240.1286288}, interhash = {5af7b26ff2fcace33426fb74902e9cc0}, intrahash = {d3fc5e2b6c2a58f46625288d40aa0de5}, isbn = {978-1-59593-820-6}, location = {Manchester, UK}, numpages = {4}, pages = {163--166}, publisher = {ACM}, series = {HT '07}, title = {Towards better understanding of folksonomic patterns}, url = {http://doi.acm.org/10.1145/1286240.1286288}, year = 2007 } @article{cattuto2009collective, abstract = {The enormous increase of popularity and use of the worldwide web has led in the recent years to important changes in the ways people communicate. An interesting example of this fact is provided by the now very popular social annotation systems, through which users annotate resources (such as web pages or digital photographs) with keywords known as “tags.” Understanding the rich emergent structures resulting from the uncoordinated actions of users calls for an interdisciplinary effort. In particular concepts borrowed from statistical physics, such as random walks (RWs), and complex networks theory, can effectively contribute to the mathematical modeling of social annotation systems. Here, we show that the process of social annotation can be seen as a collective but uncoordinated exploration of an underlying semantic space, pictured as a graph, through a series of RWs. This modeling framework reproduces several aspects, thus far unexplained, of social annotation, among which are the peculiar growth of the size of the vocabulary used by the community and its complex network structure that represents an externalization of semantic structures grounded in cognition and that are typically hard to access.}, author = {Cattuto, Ciro and Barrat, Alain and Baldassarri, Andrea and Schehr, Gregory and Loreto, Vittorio}, doi = {10.1073/pnas.0901136106}, eprint = {http://www.pnas.org/content/106/26/10511.full.pdf+html}, interhash = {0d9b41d0509bf9ee8004010663452a22}, intrahash = {0d1491f34bcd6f29c0a59e449cfdffa1}, journal = {Proceedings of the National Academy of Sciences}, number = 26, pages = {10511-10515}, title = {Collective dynamics of social annotation}, url = {http://www.pnas.org/content/106/26/10511.abstract}, volume = 106, year = 2009 } @misc{voss2006collaborative, abstract = { This paper explores the system of categories that is used to classify articles in Wikipedia. It is compared to collaborative tagging systems like del.icio.us and to hierarchical classification like the Dewey Decimal Classification (DDC). Specifics and commonalitiess of these systems of subject indexing are exposed. Analysis of structural and statistical properties (descriptors per record, records per descriptor, descriptor levels) shows that the category system of Wikimedia is a thesaurus that combines collaborative tagging and hierarchical subject indexing in a special way. }, author = {Voss, Jakob}, interhash = {7f47ede73627b6bd286a18325bc4d630}, intrahash = {269e8b153ed5856542d0a6e5b2bc7853}, note = {cite arxiv:cs/0604036Comment: 7 pages, 7 figures, 7 tables; v2 with added appendix and fixed references}, title = {Collaborative thesaurus tagging the Wikipedia way}, url = {http://arxiv.org/abs/cs/0604036}, year = 2006 } @inproceedings{dellschaft2008epistemic, abstract = {In recent literature, several models were proposed for reproducing and understanding the tagging behavior of users. They all assume that the tagging behavior is influenced by the previous tag assignments of other users. But they are only partially successful in reproducing characteristic properties found in tag streams. We argue that this inadequacy of existing models results from their inability to include user's background knowledge into their model of tagging behavior. This paper presents a generative tagging model that integrates both components, the background knowledge and the influence of previous tag assignments. Our model successfully reproduces characteristic properties of tag streams. It even explains effects of the user interface on the tag stream.}, acmid = {1379109}, address = {New York, NY, USA}, author = {Dellschaft, Klaas and Staab, Steffen}, booktitle = {Proceedings of the nineteenth ACM conference on Hypertext and hypermedia}, doi = {10.1145/1379092.1379109}, interhash = {cc0d1d4f43effbb6eb7d463422e6c00b}, intrahash = {7877bf1d91bd35067461c306b7f6fd00}, isbn = {978-1-59593-985-2}, location = {Pittsburgh, PA, USA}, numpages = {10}, pages = {71--80}, publisher = {ACM}, series = {HT '08}, title = {An epistemic dynamic model for tagging systems}, url = {http://doi.acm.org/10.1145/1379092.1379109}, year = 2008 } @article{furnas1987vocabulary, acmid = {32212}, address = {New York, NY, USA}, author = {Furnas, G. W. and Landauer, T. K. and Gomez, L. M. and Dumais, S. T.}, doi = {10.1145/32206.32212}, interhash = {b03603efa8152234684ffce8b44a5abb}, intrahash = {1a6e34f9b367fcfc67454607a9b2f8e3}, issn = {0001-0782}, issue = {11}, journal = {Commun. ACM}, month = {November}, numpages = {8}, pages = {964--971}, publisher = {ACM}, title = {The vocabulary problem in human-system communication}, url = {http://doi.acm.org/10.1145/32206.32212}, volume = 30, year = 1987 } @article{zeng2004trends, abstract = {This report analyzes the methodologies used in establishing interoperability among knowledge organization systems (KOS) such as controlled vocabularies and classification schemes that present the organized interpretation of knowledge structures. The development and trends of KOS are discussed with reference to the online era and the Internet era. Selected current projects and activities addressing KOS interoperability issues are reviewed in terms of the languages and structures involved. The methodological analysis encompasses both conventional and new methods that have proven to be widely accepted, including derivation/modeling, translation/adaptation, satellite and leaf node linking, direct mapping, co-occurrence mapping, switching, linking through a temporary union list, and linking through a thesaurus server protocol. Methods used in link storage and management, as well as common issues regarding mapping and methodological options, are also presented. It is concluded that interoperability of KOS is an unavoidable issue and process in today's networked environment. There have been and will be many multilingual products and services, with many involving various structured systems. Results from recent efforts are encouraging.}, acmid = {986356}, address = {New York, NY, USA}, author = {Zeng, Marcia Lei and Chan, Lois Mai}, doi = {10.1002/asi.10387}, interhash = {eeae36302b7daa991c6731bb7d58634b}, intrahash = {ab2a748f7a3de41f9e104c2b12f2b247}, issn = {1532-2882}, issue = {5}, journal = {J. Am. Soc. Inf. Sci. Technol.}, month = {March}, numpages = {19}, pages = {377--395}, publisher = {John Wiley \& Sons, Inc.}, title = {Trends and issues in establishing interoperability among knowledge organization systems}, url = {http://portal.acm.org/citation.cfm?id=986354.986356}, volume = 55, year = 2004 } @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 } @article{november06peterson, author = {Peterson, Elaine}, doi = {10.1045/november2006-peterson}, interhash = {11b682c7b3141988594d05dbd09fcd54}, intrahash = {9d4746291e69e3dbe5fdd1a3e38417f1}, issn = {1082-9873}, journal = {D-Lib Magazine}, month = {November }, number = 11, title = {Beneath the Metadata: Some Philosophical Problems with Folksonomy }, url = {http://www.dlib.org/dlib/november06/peterson/11peterson.html}, volume = 12, year = 2006 } @inproceedings{kipp2006exploring, abstract = {This paper examines the results of a study of the three groups involved in creating index keywords or tags: users, authors and intermediaries. Keywords from each of the three groups were compared to determine similarities and differences in term use. Comparisons suggested that there were important differences in the contexts of the three groups that should be taken into account when assigning keywords or designing systems for the organisation of information.}, author = {Kipp, Margaret E. I.}, booktitle = {ASIS\&T 2006 Information Architecture Summit}, citeulike-article-id = {581353}, citeulike-linkout-0 = {http://iasummit.org/2006/conferencedescrip.htm\#109}, interhash = {cc95302ec99e70ffae810ee377ae98e6}, intrahash = {904d826cdf2349f8b6ec802eddd6d0c4}, month = mar, posted-at = {2006-04-11 03:32:13}, priority = {3}, title = {Exploring the context of user, creator and intermediate tagging}, url = {http://iasummit.org/2006/conferencedescrip.htm\#109}, year = 2006 } @inproceedings{jonsson2007using, acmid = {1549004}, address = {Washington, DC, USA}, author = {Jonsson, Martin}, booktitle = {Proceedings of the 2007 International Conference on Mobile Data Management}, doi = {10.1109/MDM.2007.64}, interhash = {881c7cb5afbd3977564792adad50f4c8}, intrahash = {c52d309204e2801f460ae7634c3860a7}, isbn = {1-4244-1241-2}, numpages = {5}, pages = {304--308}, publisher = {IEEE Computer Society}, title = {Using a Folksonomy Approach for Location Tagging in Community Based Presence Systems}, url = {http://portal.acm.org/citation.cfm?id=1548880.1549004}, year = 2007 } @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{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{gohr2010visually, abstract = {Tags are intensively used in social platforms to annotate resources: Tagging is a social phenomenon, because users do not only annotate to organize their resources but also to associate semantics to resources contributed by third parties. This leads often to semantic ambiguities: Popular tags are associated with very disparate meanings, even to the extend that some tags (e.g. "beautiful" or "toread") are irrelevant to the semantics of the resources they annotate. We propose a method that learns a topic model for documents under a tag and visualizes the different meanings associated with the tag. Our approach deals with the following problems. First, tag miscellany is a temporal phenomenon: tags acquire multiple semantics gradually, as users apply them to disparate documents. Hence, our method must capture and visualize the evolution of the topics in a stream of documents. Second, the meanings associated to a tag must be presented in a human-understandable way; This concerns both the choice of words and the visualization of all meanings. Our method uses AdaptivePLSA, a variation of Probabilistic Latent Semantic Analysis for streams, to learn and adapt topics on a stream of documents annotated with a specific tag. We propose a visualization technique called Topic Table to visualize document prototypes derived from topics and their evolution over time. We show by a case study how our method captures the evolution of tags selected as frequent and ambiguous, and visualizes their semantics in a comprehensible way. Additionally, we show the effectiveness by adding alien resources under a tag. Our approach indeed visualizes hints to the added documents.}, address = {Kassel, Germany}, author = {Gohr, André and Spiliopoulou, Myra and Hinneburg., Alexander}, booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen {\&} Adaptivitaet}, crossref = {lwa2010}, editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, end = {2010-10-05 10:00:00}, interhash = {e7054144bb25dfac8812c15e477d1e54}, intrahash = {67dc1e470b31cb6984d5faafe8e64ce0}, room = {0446}, session = {joint1}, start = {2010-10-05 09:30:00}, title = {Visually summarizing the Evolution of Documents under a Social Tag}, track = {kdml}, url = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml27.pdf}, 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 } @inproceedings{crandall2008feedback, abstract = {A fundamental open question in the analysis of social networks is to understand the interplay between similarity and social ties. People are similar to their neighbors in a social network for two distinct reasons: first, they grow to resemble their current friends due to social influence; and second, they tend to form new links to others who are already like them, a process often termed selection by sociologists. While both factors are present in everyday social processes, they are in tension: social influence can push systems toward uniformity of behavior, while selection can lead to fragmentation. As such, it is important to understand the relative effects of these forces, and this has been a challenge due to the difficulty of isolating and quantifying them in real settings.}, address = {New York, NY, USA}, at = {2009-07-01 08:09:57}, author = {Crandall, David and Cosley, Dan and Huttenlocher, Daniel and Kleinberg, Jon and Suri, Siddharth}, booktitle = {KDD '08: Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining}, doi = {10.1145/1401890.1401914}, id = {3353096}, interhash = {07ad80d96b769ae60741f4269fccd544}, intrahash = {64d218d536296955df9780a23d9f2aec}, isbn = {978-1-60558-193-4}, location = {Las Vegas, Nevada, USA}, pages = {160--168}, priority = {3}, publisher = {ACM}, title = {Feedback effects between similarity and social influence in online communities}, url = {http://dx.doi.org/10.1145/1401890.1401914}, year = 2008 } @inproceedings{wetzker2008analyzing, abstract = {Social bookmarking systems have recently gained interestamong researches in the areas of data mining and web intelligence, as they provide a vast amount of user-generated annotations and reflect the interests of millions of people. In this paper, we discuss our initial findings obtained from analyzing a vast corpus of almost 150 million bookmarks found at del.icio.us. Apart from investigating bookmarking and tagging patterns in this data, we discuss evidence that social bookmarking systems are vulnerable to spamming and hence need to be preprocessed before any insightful analysis can be carried out. We present a method, which limits the influence of spam in social bookmarking analysis and provide conclusions and directions for future research.}, author = {Wetzker, Robert and Zimmermann, Carsten and Bauckhage, Christian}, booktitle = {Mining Social Data (MSoDa) Workshop Proceedings}, interhash = {cdd8d32ba6507335a3b856419afc71c3}, intrahash = {c71aa17db3959585ed3320dcefe7f39b}, month = {July}, organization = {ECAI 2008}, pages = {26-30}, title = {Analyzing Social Bookmarking Systems: A del.icio.us Cookbook}, url = {http://robertwetzker.com/wp-content/uploads/2008/06/wetzker_delicious_ecai2008_final.pdf}, year = 2008 } @inproceedings{auyeung2009measuring, abstract = {Collaborative tagging systems such as Delicious provide a new means of organizing and sharing resources. They also allow users to search for documents relevant to a particular topic or for other users who are experts in a particular domain. Nevertheless, identifying relevant documents and knowledgeable users is not a trivial task, especially when the volume of documents is huge and there exist spamming activities. In this paper, we discuss the notions of experts and expertise in the context of collaborative tagging systems. We propose that the level of expertise of a user in a particular topic is mainly determined by two factors: (1) there should be a relationship of mutual reinforcement between the expertise of a user and the quality of a document; and (2) an expert should be one who tends to identify useful documents before other users discover them. We propose a graph-based algorithm, SPEAR (SPamming-resistant Expertise Analysis and Ranking), which implements the above ideas for ranking users in a collaborative tagging system. We carry out experiments on both simulated data sets and real-world data sets obtained from Delicious, and show that SPEAR is more resistant to spammers than other methods such as the HITS algorithm and simple statistical measures.}, author = {{Au Yeung}, Ching Man and Noll, Michael G. and Gibbins, Nicholas and Meinel, Christoph and Shadbolt, Nigel}, booktitle = {WebSci'09: Web Science Conference 2009 - Society On-Line, Athens, Greece, 18-20 March, 2009}, interhash = {dd6885ca4e2293f2d70852ca0d55f239}, intrahash = {4831ad30a8a37f6b5d1adf3d3d717713}, month = {March}, title = {On Measuring Expertise in Collaborative Tagging Systems}, url = {http://journal.webscience.org/109/}, year = 2009 } @article{steels2006collaborative, author = {Steels, Luc}, file = {:steels2006collaborative.pdf:PDF}, interhash = {ddd8c61cc9cd490b99413b5781c332b4}, intrahash = {9e624e613d0dab7b7332d6569c8b2607}, journal = {Pragmatics and Cognition}, number = 2, pages = {275-285}, title = {Collaborative tagging as distributed cognition}, url = {http://www.isrl.uiuc.edu/~amag/langev/paper/steels06tagging.html}, volume = 14, year = 2006 } @inproceedings{antonellis2009tagging, abstract = {Web search queries capture the information need of search engine users. Search engines store these queries in their logs and analyze them to guide their search results.In this work, we argue that not only a search engine can benefit from data stored in these logs, but also the web users. We first show how clickthrough logs can be collected in a distributed fashion using the http referer field in web server access logs. We then perform a set of experiments to study the information value of search engine queries when treated as "tags" or "labels" for the web pages that both appear as a result and the user actually clicks on. We ask how much extra information these query tags provide for web pagesby comparing them to tags from the del.icio.us bookmarking site and to the pagetext. We find that query tags can provide substantially many (on average 250 tags per URL), new tags (on average 125 tags per URL are not present in the pagetext) for a large fraction of the Web.}, address = {New York, NY, USA}, author = {Antonellis, Ioannis and Garcia-Molina, Hector and Karim, Jawed}, booktitle = {WSDM (Late Breaking-Results)}, crossref = {conf/wsdm/2009}, date = {2009-03-12}, editor = {Baeza-Yates, Ricardo A. and Boldi, Paolo and Ribeiro-Neto, Berthier A. and Cambazoglu, Berkant Barla}, interhash = {d7009d789ebc4efe38749a1078a06086}, intrahash = {70539954a20f7d03a1f21764ff62c0ff}, isbn = {978-1-60558-390-7}, publisher = {ACM}, title = {Tagging with Queries: How and Why?}, url = {http://www.wsdm2009.org/wsdm2009_antonellis.pdf}, year = 2009 } @inproceedings{grahl2007conceptuala, abstract = {Currently, social bookmarking systems provide intuitive support for browsing locally their content. A global view is usually presented by the tag cloud of thesystem, but it does not allow a conceptual drill-down, e. g., along a conceptual hierarchy. In this paper, we present a clustering approach for computing such a conceptual hierarchy for a given folksonomy. The hierarchy is complemented with ranked lists of users and resources most related to each cluster. The rankings are computed using our FolkRank algorithm. We have evaluated our approach on large scale data from the del.icio.us bookmarking system.}, address = {Graz, Austria}, author = {Grahl, Miranda and Hotho, Andreas and Stumme, Gerd}, booktitle = {7th International Conference on Knowledge Management (I-KNOW '07)}, interhash = {5cf58d2fdd3c17f0b0c54ce098ff5b60}, intrahash = {334d3ab11400c4a3ea3ed5b1e95c1855}, issn = {0948-695x}, month = {September}, pages = {356-364}, publisher = {Know-Center}, title = {Conceptual Clustering of Social Bookmarking Sites}, url = {http://www.tagora-project.eu/wp-content/2007/06/grahl_iknow07.pdf}, year = 2007 }