@inproceedings{chi2008understanding, abstract = {Given the rise in popularity of social tagging systems, it seems only natural to ask how efficient is the organically evolved tagging vocabulary in describing underlying document objects? Does this distributed process really provide a way to circumnavigate the traditional "vocabulary problem" with ontology? We analyze a social tagging site, namely del.icio.us, with information theory in order to evaluate the efficiency of this social tagging site for encoding navigation paths to information sources. We show that information theory provides a natural and interesting way to understand this efficiency - or the descriptive, encoding power of tags. Our results indicate the efficiency of tags appears to be waning. We discuss the implications of our findings and provide insight into how our methods can be used to design more usable social tagging software.}, acmid = {1379110}, added-at = {2011-12-05T18:36:22.000+0100}, address = {New York, NY, USA}, author = {Chi, Ed H. and Mytkowicz, Todd}, biburl = {http://www.bibsonomy.org/bibtex/2d44d1c9a48f5b676388ffbc90c7577ba/jaeschke}, booktitle = {Proceedings of the nineteenth ACM conference on Hypertext and hypermedia}, doi = {10.1145/1379092.1379110}, interhash = {81c80283290d396a41015d0df11822c7}, intrahash = {d44d1c9a48f5b676388ffbc90c7577ba}, isbn = {978-1-59593-985-2}, keywords = {collaborative folksonomy information social tagging theory}, location = {Pittsburgh, PA, USA}, numpages = {8}, pages = {81--88}, publisher = {ACM}, timestamp = {2011-12-05T18:36:22.000+0100}, title = {Understanding the efficiency of social tagging systems using information theory}, url = {http://doi.acm.org/10.1145/1379092.1379110}, year = 2008 } @inproceedings{krause2008logsonomy, abstract = {Social bookmarking systems constitute an established part of the Web 2.0. In such systems users describe bookmarks by keywords called tags. The structure behind these social systems, called folksonomies, can be viewed as a tripartite hypergraph of user, tag and resource nodes. This underlying network shows specific structural properties that explain its growth and the possibility of serendipitous exploration. Today’s search engines represent the gateway to retrieve information from the World Wide Web. Short queries typically consisting of two to three words describe a user’s information need. In response to the displayed results of the search engine, users click on the links of the result page as they expect the answer to be of relevance. This clickdata can be represented as a folksonomy in which queries are descriptions of clicked URLs. The resulting network structure, which we will term logsonomy is very similar to the one of folksonomies. In order to find out about its properties, we analyze the topological characteristics of the tripartite hypergraph of queries, users and bookmarks on a large snapshot of del.icio.us and on query logs of two large search engines. All of the three datasets show small world properties. The tagging behavior of users, which is explained by preferential attachment of the tags in social bookmark systems, is reflected in the distribution of single query words in search engines. We can conclude that the clicking behaviour of search engine users based on the displayed search results and the tagging behaviour of social bookmarking users is driven by similar dynamics.}, added-at = {2011-01-27T12:08:28.000+0100}, address = {New York, NY, USA}, author = {Krause, Beate and Jäschke, Robert and Hotho, Andreas and Stumme, Gerd}, biburl = {http://www.bibsonomy.org/bibtex/2e64d14f3207766f4afc65983fa759ffe/jaeschke}, booktitle = {HT '08: Proceedings of the Nineteenth ACM Conference on Hypertext and Hypermedia}, doi = {10.1145/1379092.1379123}, interhash = {6d34ea1823d95b9dbf37d4db4d125d2a}, intrahash = {e64d14f3207766f4afc65983fa759ffe}, isbn = {978-1-59593-985-2}, keywords = {2008 engine information l3s logsonomy myown retrieval search wp5 analysis network sna social}, location = {Pittsburgh, PA, USA}, pages = {157--166}, publisher = {ACM}, timestamp = {2011-01-27T12:08:28.000+0100}, title = {Logsonomy - Social Information Retrieval with Logdata}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/krause2008logsonomy.pdf}, vgwort = {17}, year = 2008 } @phdthesis{peters2009folksonomies, added-at = {2011-01-26T12:03:05.000+0100}, author = {Peters, Isabella}, biburl = {http://www.bibsonomy.org/bibtex/2a25702677dc406b1be7878215277050c/jaeschke}, interhash = {f52c87372515e42e0cde602a2fe8da39}, intrahash = {a25702677dc406b1be7878215277050c}, keywords = {folksonomy information knowledge representation retrieval wissen}, school = {Universität Düsseldorf}, timestamp = {2011-01-26T12:03:05.000+0100}, title = {Folksonomies in Wissensrepräsentation und Information Retrieval}, type = {PhD thesis}, year = 2009 } @article{stock2008folksonomies, abstract = {Folksonomies in Wissensrepräsentation und Information Retrieval. Die populären Web 2.0-Dienste werden von Prosumern – Produzenten und gleichsam Konsumenten – nicht nur dazu genutzt, Inhalte zu produzieren, sondern auch, um sie inhaltlich zu erschließen. Folksonomies erlauben es dem Nutzer, Dokumente mit eigenen Schlagworten, sog. Tags, zu beschreiben, ohne dabei auf gewisse Regeln oder Vorgaben achten zu müssen. Neben einigen Vorteilen zeigen Folksonomies aber auch zahlreiche Schwächen (u. a. einen Mangel an Präzision). Um diesen Nachteilen größtenteils entgegenzuwirken, schlagen wir eine Interpretation der Tags als natürlichsprachige Wörter vor. Dadurch ist es uns möglich, Methoden des Natural Language Processing (NLP) auf die Tags anzuwenden und so linguistische Probleme der Tags zu beseitigen. Darüber hinaus diskutieren wir Ansätze und weitere Vorschläge (Tagverteilungen, Kollaboration und akteurspezifische Aspekte) hinsichtlich eines Relevance Rankings von getaggten Dokumenten. Neben Vorschlägen auf ähnliche Dokumente („more like this!“) erlauben Folksonomies auch Hinweise auf verwandte Nutzer und damit auf Communities („more like me!“). Folksonomies in Knowledge Representation and Information Retrieval In Web 2.0 services “prosumers” – producers and consumers – collaborate not only for the purpose of creating content, but to index these pieces of information as well. Folksonomies permit actors to describe documents with subject headings, “tags“, without regarding any rules. Apart from a lot of benefits folksonomies have many shortcomings (e.g., lack of precision). In order to solve some of the problems we propose interpreting tags as natural language terms. Accordingly, we can introduce methods of NLP to solve the tags’ linguistic problems. Additionally, we present criteria for tagged documents to create a ranking by relevance (tag distribution, collaboration and actor-based aspects). Besides recommending similar documents („more like this!“) folksonomies can be used for the recommendation of similar users and communities („more like me!“).}, added-at = {2011-01-26T11:41:50.000+0100}, author = {Peters, Isabella and Stock, Wolfgang G.}, biburl = {http://www.bibsonomy.org/bibtex/216fa5c5fc155e296ff885bf62d1a1230/jaeschke}, interhash = {a9a40e30db7636b46aca513bb73c6689}, intrahash = {16fa5c5fc155e296ff885bf62d1a1230}, journal = {Information - Wissenschaft und Praxis}, keywords = {folksonomy information representation retrieval wissen}, number = 2, pages = {77--90}, timestamp = {2011-01-26T11:41:50.000+0100}, title = {Folksonomies in Wissensrepräsentation und Information Retrieval}, url = {http://www.phil-fak.uni-duesseldorf.de/infowiss/mitarbeiter/wissenschaftliche-mitarbeiter-hilfskraefte/isabella-peters/012-folksonomies-in-wissensrepraesentation-und-information-retrieval/}, volume = 59, year = 2008 } @book{tufte2001visual, added-at = {2009-11-17T11:19:31.000+0100}, asin = {0961392142}, author = {Tufte, Edward R.}, biburl = {http://www.bibsonomy.org/bibtex/29c028ebcb336380cb02e2a4beaa14d54/jaeschke}, description = {A timeless classic in how complex information should be presented graphically. The Strunk & White of visual design. Should occupy a place of honor--within arm's reach--of everyone attempting to understand or depict numerical data graphically. The design of the book is an exemplar of the principles it espouses: elegant typography and layout, and seamless integration of lucid text and perfectly chosen graphical examples. Very Highly Recommended.}, dewey = {001.4226}, ean = {9780961392147}, edition = {Second}, interhash = {9900880e451150c1b06ede3c780c062b}, intrahash = {9c028ebcb336380cb02e2a4beaa14d54}, isbn = {0961392142}, keywords = {data information mining toread visualization}, publisher = {Graphics Press}, timestamp = {2009-11-17T11:19:31.000+0100}, title = {The Visual Display of Quantitative Information}, url = {http://www.amazon.com/Visual-Display-Quantitative-Information-2nd/dp/0961392142%3FSubscriptionId%3D192BW6DQ43CK9FN0ZGG2%26tag%3Dws%26linkCode%3Dxm2%26camp%3D2025%26creative%3D165953%26creativeASIN%3D0961392142}, year = 2001 } @article{jarvelin2002cumulated, abstract = {Modern large retrieval environments tend to overwhelm their users by their large output. Since all documents are not of equal relevance to their users, highly relevant documents should be identified and ranked first for presentation. In order to develop IR techniques in this direction, it is necessary to develop evaluation approaches and methods that credit IR methods for their ability to retrieve highly relevant documents. This can be done by extending traditional evaluation methods, that is, recall and precision based on binary relevance judgments, to graded relevance judgments. Alternatively, novel measures based on graded relevance judgments may be developed. This article proposes several novel measures that compute the cumulative gain the user obtains by examining the retrieval result up to a given ranked position. The first one accumulates the relevance scores of retrieved documents along the ranked result list. The second one is similar but applies a discount factor to the relevance scores in order to devaluate late-retrieved documents. The third one computes the relative-to-the-ideal performance of IR techniques, based on the cumulative gain they are able to yield. These novel measures are defined and discussed and their use is demonstrated in a case study using TREC data: sample system run results for 20 queries in TREC-7. As a relevance base we used novel graded relevance judgments on a four-point scale. The test results indicate that the proposed measures credit IR methods for their ability to retrieve highly relevant documents and allow testing of statistical significance of effectiveness differences. The graphs based on the measures also provide insight into the performance IR techniques and allow interpretation, for example, from the user point of view.}, added-at = {2009-11-03T15:41:30.000+0100}, address = {New York, NY, USA}, author = {Järvelin, Kalervo and Kekäläinen, Jaana}, biburl = {http://www.bibsonomy.org/bibtex/212176d90012ed75f57996af0b9240d02/jaeschke}, description = {Cumulated gain-based evaluation of IR techniques}, doi = {10.1145/582415.582418}, interhash = {c46348827790803e8e7465ffd1a13376}, intrahash = {12176d90012ed75f57996af0b9240d02}, issn = {1046-8188}, journal = {ACM Transactions on Information Systems}, keywords = {evaluation information ir retrieval}, month = oct, number = 4, pages = {422--446}, publisher = {ACM}, timestamp = {2009-11-03T15:41:30.000+0100}, title = {Cumulated gain-based evaluation of IR techniques}, url = {http://portal.acm.org/citation.cfm?id=582418}, volume = 20, year = 2002 } @inproceedings{jarvelin2000ir, abstract = {This paper proposes evaluation methods based on the use of non-dichotomous relevance judgements in IR experiments. It is argued that evaluation methods should credit IR methods for their ability to retrieve highly relevant documents. This is desirable from the user point of view in modern large IR environments. The proposed methods are (1) a novel application of P-R curves and average precision computations based on separate recall bases for documents of different degrees of relevance, and (2) two novel measures computing the cumulative gain the user obtains by examining the retrieval result up to a given ranked position. We then demonstrate the use of these evaluation methods in a case study on the effectiveness of query types, based on combinations of query structures and expansion, in retrieving documents of various degrees of relevance. The test was run with a best match retrieval system (In-Query1) in a text database consisting of newspaper articles. The results indicate that the tested strong query structures are most effective in retrieving highly relevant documents. The differences between the query types are practically essential and statistically significant. More generally, the novel evaluation methods and the case demonstrate that non-dichotomous relevance assessments are applicable in IR experiments, may reveal interesting phenomena, and allow harder testing of IR methods.}, added-at = {2009-11-03T13:28:34.000+0100}, address = {New York, NY, USA}, author = {Järvelin, Kalervo and Kekäläinen, Jaana}, biburl = {http://www.bibsonomy.org/bibtex/212592d5f805db5bd127ee5abae1a4325/jaeschke}, booktitle = {SIGIR '00: Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, description = {IR evaluation methods for retrieving highly relevant documents}, doi = {10.1145/345508.345545}, interhash = {a62a44c48d24acc64cd6713f21111d72}, intrahash = {12592d5f805db5bd127ee5abae1a4325}, isbn = {1-58113-226-3}, keywords = {evaluation information ir retrieval}, location = {Athens, Greece}, pages = {41--48}, publisher = {ACM}, timestamp = {2009-11-03T13:28:34.000+0100}, title = {IR evaluation methods for retrieving highly relevant documents}, url = {http://portal.acm.org/citation.cfm?id=345545}, year = 2000 } @book{baeza-yates1999modern, abstract = {This is a rigorous and complete textbook for a first course on information retrieval from the computer science (as opposed to a user-centred) perspective. The advent of the Internet and the enormous increase in volume of electronically stored information generally has led to substantial work on IR from the computer science perspective - this book provides an up-to-date student oriented treatment of the subject.}, added-at = {2009-10-17T10:08:47.000+0200}, address = {Boston, MA, USA}, author = {Baeza-Yates, Ricardo A. and Ribeiro-Neto, Berthier}, biburl = {http://www.bibsonomy.org/bibtex/2ead0b4af17c94074fe1c774d2f267617/jaeschke}, interhash = {6f78177742b3c836218aacfc7fc4c43c}, intrahash = {ead0b4af17c94074fe1c774d2f267617}, isbn = {020139829X}, keywords = {book information ir retrieval web}, publisher = {Addison-Wesley Longman Publishing Co., Inc.}, timestamp = {2009-10-17T10:08:47.000+0200}, title = {Modern Information Retrieval}, url = {http://portal.acm.org/citation.cfm?id=553876}, year = 1999 } @inproceedings{chi2008understanding, abstract = {Given the rise in popularity of social tagging systems, it seems only natural to ask how efficient is the organically evolved tagging vocabulary in describing underlying document objects? Does this distributed process really provide a way to circumnavigate the traditional "vocabulary problem" with ontology? We analyze a social tagging site, namely del.icio.us, with information theory in order to evaluate the efficiency of this social tagging site for encoding navigation paths to information sources. We show that information theory provides a natural and interesting way to understand this efficiency - or the descriptive, encoding power of tags. Our results indicate the efficiency of tags appears to be waning. We discuss the implications of our findings and provide insight into how our methods can be used to design more usable social tagging software.}, added-at = {2009-08-03T10:04:08.000+0200}, address = {New York, NY, USA}, author = {Chi, Ed H. and Mytkowicz, Todd}, biburl = {http://www.bibsonomy.org/bibtex/2dfa880e6d3e33d0aeb357396fb1833cd/jaeschke}, booktitle = {HT '08: Proceedings of the nineteenth ACM conference on Hypertext and hypermedia}, description = {Understanding the efficiency of social tagging systems using information theory}, doi = {10.1145/1379092.1379110}, interhash = {81c80283290d396a41015d0df11822c7}, intrahash = {dfa880e6d3e33d0aeb357396fb1833cd}, isbn = {978-1-59593-985-2}, keywords = {bookmarking efficiency folksonomy information social tagging theory}, location = {Pittsburgh, PA, USA}, pages = {81--88}, publisher = {ACM}, timestamp = {2009-08-03T10:04:08.000+0200}, title = {Understanding the efficiency of social tagging systems using information theory}, url = {http://portal.acm.org/citation.cfm?id=1379110&coll=GUIDE&dl=GUIDE&CFID=37458772&CFTOKEN=13998061&ret=1}, year = 2008 } @article{macgregor2006collaborative, abstract = {The purpose of the paper is to provide an overview of the collaborative tagging phenomenon and explore some of the reasons for its emergence. Design/methodology/approach - The paper reviews the related literature and discusses some of the problems associated with, and the potential of, collaborative tagging approaches for knowledge organisation and general resource discovery. A definition of controlled vocabularies is proposed and used to assess the efficacy of collaborative tagging. An exposition of the collaborative tagging model is provided and a review of the major contributions to the tagging literature is presented. Findings - There are numerous difficulties with collaborative tagging systems (e.g. low precision, lack of collocation, etc.) that originate from the absence of properties that characterise controlled vocabularies. However, such systems can not be dismissed. Librarians and information professionals have lessons to learn from the interactive and social aspects exemplified by collaborative tagging systems, as well as their success in engaging users with information management. The future co-existence of controlled vocabularies and collaborative tagging is predicted, with each appropriate for use within distinct information contexts: formal and informal. Research limitations/implications - Librarians and information professional researchers should be playing a leading role in research aimed at assessing the efficacy of collaborative tagging in relation to information storage, organisation, and retrieval, and to influence the future development of collaborative tagging systems. Practical implications - The paper indicates clear areas where digital libraries and repositories could innovate in order to better engage users with information. Originality/value - At time of writing there were no literature reviews summarising the main contributions to the collaborative tagging research or debate.}, added-at = {2008-10-27T09:14:27.000+0100}, author = {Macgregor, George and McCulloch, Emma}, biburl = {http://www.bibsonomy.org/bibtex/297d3915ead822cfa033fc821b424e437/jaeschke}, doi = {10.1108/00242530610667558}, editor = {McMenemy, David}, interhash = {8d7a458fb6f9ff722c7d02104ec6dbd0}, intrahash = {97d3915ead822cfa033fc821b424e437}, issn = {0024-2535}, journal = {Library Review}, keywords = {bookmarking classification folksonomy information knowledge management retrieval social tagging}, number = 5, pages = {291-300}, publisher = {Emerald Group Publishing Limited}, timestamp = {2008-10-27T09:14:27.000+0100}, title = {Collaborative Tagging as a Knowledge Organisation and Resource Discovery Tool}, url = {http://www.emeraldinsight.com/10.1108/00242530610667558}, volume = 55, year = 2006 } @inproceedings{hotho2006information, abstract = {Social bookmark tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. The reason for their immediate success is the fact that no specific skills are needed for participating. At the moment, however, the information retrieval support is limited. We present a formal model and a new search algorithm for folksonomies, called FolkRank, that exploits the structure of the folksonomy. The proposed algorithm is also applied to find communities within the folksonomy and is used to structure search results. All findings are demonstrated on a large scale dataset.}, added-at = {2007-02-01T14:04:37.000+0100}, address = {Heidelberg}, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, biburl = {http://www.bibsonomy.org/bibtex/23c301945817681d637ee43901c016939/jaeschke}, booktitle = {The Semantic Web: Research and Applications}, editor = {Sure, York and Domingue, John}, interhash = {10ec64d80b0ac085328a953bb494fb89}, intrahash = {3c301945817681d637ee43901c016939}, keywords = {2006 folkrank folksonomy graph iccs_example information l3s mining myown ol_tut2010 rank ranking retrieval search seminar2006 trias_example webzu pagerank}, month = {June}, pages = {411-426}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2007-02-01T14:04:37.000+0100}, title = {Information Retrieval in Folksonomies: Search and Ranking}, volume = 4011, year = 2006 } @inproceedings{827147, abstract = {In this paper, we propose a method for extracting bibliographic attributes from reference strings captured using Optical Character Recognition (OCR) and an extended hidden Markov model. Bibliographic attribute extraction can be used in two ways. One is reference parsing in which attribute values are extracted from OCR-processed references for bibliographic matching. The other is reference alignment in which attribute values are aligned to the bibliographic record to enrich the vocabulary of the bibliographic database. In this paper, we first propose a statistical model for attribute extraction that represents both the syntactical structure of references and OCR error patterns. Then, we perform experiments using bibliographic references obtained from scanned images of papers in journals and transactions and show that useful attribute values are extracted from OCR-processed references. We also show that the proposed model has advantages in reducing the cost of preparing training data, a critical problem in rule-based systems.}, added-at = {2006-05-10T16:00:48.000+0200}, address = {Washington, DC, USA}, author = {Takasu, Atsuhiro}, biburl = {http://www.bibsonomy.org/bibtex/273b4dff8c6fac17b3ea377ed5b162540/jaeschke}, booktitle = {JCDL '03: Proceedings of the 3rd ACM/IEEE-CS joint conference on Digital libraries}, interhash = {324c5995d000ceffa826eb2950dcd52e}, intrahash = {73b4dff8c6fac17b3ea377ed5b162540}, isbn = {0-7695-1939-3}, keywords = {extraction information ie bibliographic}, pages = {49--60}, publisher = {IEEE Computer Society}, timestamp = {2006-05-10T16:00:48.000+0200}, title = {Bibliographic attribute extraction from erroneous references based on a statistical model}, year = 2003 } @inproceedings{pm04accurate, added-at = {2006-04-19T15:29:08.000+0200}, author = {Peng, Fuchun and McCallum, Andrew}, biburl = {http://www.bibsonomy.org/bibtex/28d04bc19e470fe4b98e15a27a1e6e7e9/jaeschke}, booktitle = {HLT-NAACL}, description = {dblp}, ee = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/176_Paper.pdf}, interhash = {8f9ef6b359fef3bd08bfed653fe1bb55}, intrahash = {8d04bc19e470fe4b98e15a27a1e6e7e9}, keywords = {extraction information}, pages = {329-336}, timestamp = {2006-04-19T15:29:08.000+0200}, title = {Accurate Information Extraction from Research Papers using Conditional Random Fields}, url = {http://dblp.uni-trier.de/db/conf/naacl/naacl2004.html#PengM04}, year = 2004 } @unpublished{McCallumMALLET, added-at = {2006-04-11T14:59:28.000+0200}, author = {McCallum, Andrew Kachites}, biburl = {http://www.bibsonomy.org/bibtex/26dbb7b45a3a53997359a5e3c2677dc52/jaeschke}, interhash = {a41946adb992cd2c89158609adc0d83f}, intrahash = {6dbb7b45a3a53997359a5e3c2677dc52}, keywords = {extraction learning information mallet machine}, note = {http://mallet.cs.umass.edu}, timestamp = {2006-04-11T14:59:28.000+0200}, title = {{MALLET: A Machine Learning for Language Toolkit}}, url = {http://mallet.cs.umass.edu}, year = 2002 }