@techreport{Alfaro2007atw, title = {Assigning Trust To Wikipedia Content}, address = {Santa Cruz, CA, USA}, author = {B.T. Adler and J. Benterou and K. Chatterjee and L. de Alfaro and I. Pye and V. Raman}, institution = {School of Engineering, University of California}, number = {UCSC-CRL-07-09}, year = 2007, url = {http://www.soe.ucsc.edu/~luca/papers/07/trust-techrep.pdf}, abstract = {The Wikipedia is a collaborative encyclopedia: anyone can contribute to its articles simply by clicking on an ``edit'' button. The open nature of the Wikipedia has been key to its success, but has also created a challenge: how can readers form an informed opinion on its reliability? We propose a system that computes quantitative values of trust for the text in Wikipedia articles; these trust values provide an indication of text reliability. The system uses as input the revision history of each article, as well as information about the reputation of the contributing authors, as provided by a reputation system. The trust of a word in an article is computed on the basis of the reputation of the original author of the word, as well as the reputation of all authors who edited the text in proximity of the word. The algorithm computes word trust values that vary smoothly across the text; the trust values can be visualized using varying text-background colors. The algorithm ensures that all changes to an article text are reflected in the trust values, preventing surreptitious content changes. We have implemented the proposed system, and we have used it to compute and display the trust of the text of thousands of articles of the English Wikipedia. To validate our trust-computation algorithms, we show that text labeled as low-trust has a significantly higher probability of being edited in the future than text labeled as high-trust. Anecdotal evidence seems to corroborate this validation: in practice, readers find the trust information valuable. }, biburl = {http://www.bibsonomy.org/bibtex/2f0a6f5f09f02276c6090e894cba1779b/brightbyte}, keywords = {wikipedia quality annotation reputation} } @techreport{Alfaro2008rcdr, title = {Robust Content-Driven Reputation}, address = {Santa Cruz, CA, USA}, author = {K. Chatterjee and L. de Alfaro and I. Pye}, institution = {School of Engineering, University of California}, number = {UCSC-SOE-08-09}, year = 2008, url = {http://www.soe.ucsc.edu/~luca/papers/08/ucsc-soe-08-09.pdf}, abstract = {In content-driven reputation systems for collaborative content, users gain or lose reputation according to how their contributions fare: authors of long-lived contributions gain reputation, while authors of reverted contributions lose reputation. Existing content-driven systems are prone to Sybil attacks, in which multiple identities, controlled by the same person, perform coordinated actions to increase their reputation. We show that content-driven reputation systems can be made resistent to such attacks by taking advantage of the fact that the reputation increments and decrements depend on content modifications, which are visible to all. We present an algorithm for content-driven reputation that prevents a set of identities from increasing their maximum reputation without doing any useful work. A variation of the algorithm ensures that the reputation of each identity which performs only non-useful work decreases. Here, work is considered useful if it causes content to evolve in a direction that is consistent with the actions of high-reputation users. We argue that the content modifications that require no effort, such as the insertion or deletion of arbitrary text, are invariably non-useful. We prove a truthfullness result for the resulting system, stating that users who wish to perform a contribution do not gain by employing complex contribution schemes, compared to simply performing the contribution at once. In particular, splitting the contribution in multiple portions, or employing the coordinated actions of multiple identities, do not yield additional reputation. Taken together, these results indicate that content-driven systems can be made robust with respect to Sybil attacks. }, biburl = {http://www.bibsonomy.org/bibtex/2c1c9eb9efc1aa2297bfe214b3931d876/brightbyte}, keywords = {quality wikipedia reputation annotation} } @techreport{Alfaro2008mac, title = {Measuring Author Contributions to the Wikipedia}, address = {Santa Cruz, CA, USA}, author = {B.T. Adler and L. de Alfaro and I. Pye and V. Raman}, institution = {School of Engineering, University of California}, number = {UCSC-SOE-08-08}, year = 2008, url = {http://www.soe.ucsc.edu/~luca/papers/08/ucsc-soe-08-08.pdf}, abstract = {We consider the problem of measuring user contributions to versioned, collaborative bodies of information, such as wikis. Measuring the contributions of individual authors can be used to divide revenue, to recognize merit, to award status promotions, and to choose the order of authors when citing the content. In the context of the Wikipedia, previous works on author contribution estimation have focused on two criteria: the total text created, and the total number of edits performed. We show that neither of these criteria work well: both techniques are vulnerable to manipulation, and the total-text criterion fails to reward people who polish or re-arrange the content. We consider and compare various alternative criteria that take into account the quality of a contribution, in addition to the quantity, and we analyze how the criteria differ in the way they rank authors according to their contributions. As an outcome of this study, we propose to adopt total edit longevity as a measure of author contribution. Edit longevity is resistant to simple attacks, since edits are counted towards an author's contribution only if other authors accept the contribution. Edit longevity equally rewards people who create content, and people who rearrange or polish the content. Finally, edit longevity distinguishes the people who contribute little (who have contribution close to zero) from spammers or vandals, whose contribution quickly grows negative. }, biburl = {http://www.bibsonomy.org/bibtex/2597bd830925a7ceb1e6dc6035ea4a276/brightbyte}, keywords = {reputation quality annotation wikipedia} } @inproceedings{stvilia2005aiq, title = {Assessing information quality of a community-based encyclopedia}, author = {B. Stvilia and M.B. Twidale and L.C. Smith and L. Gasser}, booktitle = {Proceedings of the International Conference on Information Quality}, pages = {442--454}, year = 2005, biburl = {http://www.bibsonomy.org/bibtex/242766c70b10104e7f379a7872b409dec/brightbyte}, keywords = {wikipedia quality} } @inproceedings{hammwohner:iaw, title = {{Interlingual Aspects if Wikipedia’s Quality}}, author = {Rainer Hammwöhner}, booktitle = {12th International Conference on Information Quality (ICIQ-2007)}, editor = {Mary Ann Robbert and M. Lynne Markus and Barbara Klein}, note = {Universität Regensburg}, publisher = {M.I.T.}, year = 2007, url = {http://mitiq.mit.edu/iciq/PDF/INTERLINGUAL%20ASPECTS%20OF%20WIKIPEDIAS%20QUALITY.pdf}, biburl = {http://www.bibsonomy.org/bibtex/2d4a85aab7e99f710f363fc9e18264bc3/brightbyte}, keywords = {wikiepdia quality} } @article{giles2005, title = {Internet encyclopaedias go head to head}, author = {Jim Giles}, journal = {Nature}, pages = {900-901}, volume = 438, year = 2005, url = {http://www.nature.com/nature/journal/v438/n7070/pdf/438900a.pdf}, biburl = {http://www.bibsonomy.org/bibtex/2f5fce10ca37d365d082e9e254352e51e/brightbyte}, keywords = {WW-SHOULD quality wikipedia} } @phdthesis{Reagle2008, title = {In good faith: {Wikipedia} collaboration and the pursuit of the universal encyclopedia}, address = {New York, NY}, author = {Joseph Reagle}, month = {May}, school = {New York University}, year = 2008, url = {http://reagle.org/joseph/2008/03/dsrtn-in-good-faith}, biburl = {http://www.bibsonomy.org/bibtex/26e0cb2fe77e4d119354a806b93ed06a9/brightbyte}, keywords = {collaboration quality WW-SHOULD community wikipedia} } @article{hammwohner:qw, title = {{Qualitätsaspekte der Wikipedia}}, author = {R. Hammwöhner}, journal = {Kommunikation@ gesellschaft}, note = {Wikis - Diskurse, Theorien und Anwendungen}, volume = {Jg. 8}, year = 2007, biburl = {http://www.bibsonomy.org/bibtex/214aed058f5af8ae66e7e9463e83f6c87/brightbyte}, keywords = {WW-MUST wikipedia quality} } @article{wilkinson2007caq, title = {{Cooperation and quality in wikipedia}}, author = {D.M. Wilkinson and B.A. Huberman}, journal = {Proceedings of the 2007 international symposium on Wikis}, pages = {157--164}, publisher = {ACM Press New York, NY, USA}, year = 2007, biburl = {http://www.bibsonomy.org/bibtex/2c7ea7ec7fabfb9583b2d6707f9d359f3/brightbyte}, keywords = {wikipedia quality cooperation} } @inproceedings{Hammwoener2007Prem, title = {Semantic Wikipedia - Checking the Premises}, address = {Bonn}, author = {Rainer Hammw\"{o}hner}, booktitle = {The Social Semantic Web 2007 - Proceedings of the 1st Conference on Social Semantic Web}, organization = {Universit\\"{a}t Leipzig, Germany}, publisher = {Gesellschaft f\\"{u}r Informatik}, school = {Universit\\"{a}t Regensburg, Germany}, series = {Lecture Notes in Informatics}, year = 2007, id = {2157227}, priority = {2}, description = {stuff from citeyoulike}, abstract = {Enhancing Wikipedia by means of semantic representations seems to be a promising issue. From a formal or technical point of view there are no major obstacles in the way. Nevertheless, a close look at Wikipedia, its structure and contents reveals that some questions have to be answered in advance. This paper will deal with these questions and present some first results based on empirical findings.}, biburl = {http://www.bibsonomy.org/bibtex/242632ca4229fdf7ffc7b713ae6530790/brightbyte}, keywords = {thesaurus quality wikipedia taxonomy WW-MUST} } @book{citeulike:2168280, title = {Qualit\"{a}tsmessungen an der Wikipedia. Konstruktion von Qualit\"{a}t ? eine Metaanalyse}, author = {Henrik Grotjahn}, month = {October}, publisher = {{Vdm Verlag Dr. M\"{u}ller}}, year = 2007, url = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/3836430452}, id = {2168280}, priority = {2}, isbn = {3836430452}, description = {stuff from citeyoulike}, biburl = {http://www.bibsonomy.org/bibtex/239535e420c47e214e6e1525c5a9f9924/brightbyte}, keywords = {statistics wikipedia quality} } @article{citeulike:2264075, title = {Qualit\"{a}tsaspekte der Wikipedia}, author = {Rainer Hammw\"{o}hner}, journal = {Kommunikation@gesellschaft}, number = {B3}, year = 2007, url = {http://www.doaj.org/doaj?func=abstract\&\#38;id=219145\&\#38;q1=Qualit\%C3\%A4tsaspekte\%20der\%20Wikipedia\&\#38;f1=all\&\#38;b1=and\&\#38;q2=\&\#38;f2=all\&\#38;recNo=1}, id = {2264075}, priority = {3}, description = {stuff from citeyoulike}, abstract = {Eine kritische Diskussion \"{u}ber ihre Verl\"{a}sslichkeit begleitet die Entwicklung der Wikipedia von Beginn an. Mittlerweile liegen einige Publikationen vor, die sich mit der Qualit\"{a}t dieser neuen Enzyklop\"{a}die befassen. In diesem Betrag wird ein kurzer \"{U}berblick \"{u}ber mehrere dieser Arbeiten gegeben. Anschlie{\ss}end werden zwei eigene Studien vorgestellt, die sich mit Qualit\"{a}tsaspekten befassen, die bisher weniger ber\"{u}cksichtigt wurden. In der ersten Studie wird die Abdeckung eines gut umgrenzten Themenkomplexes – Shakespeare’s Werk – in mehreren Wikipedias untersucht. Die zweite Studie befasst sich mit der Qualit\"{a}t der Wissensorganisation in der Wikipedia.}, biburl = {http://www.bibsonomy.org/bibtex/23ec592694eb740a768101f9e8f0a4a82/brightbyte}, keywords = {wikipedia quality} }