BibSonomyburst/group/kdeBibSonomy RSS feed for /group/kde2012-02-15T03:00:51+01:00http://www.bibsonomy.org/bibtex/287d6883ebd98e8810be45d7e7e4ade96/hothohotho2012-02-14T08:29:50+01:002012 bookmarking collaborative folksonomy myown recommender social tagging <span class="authorEditorList"><a href="/author/Balby Marinho">L. Balby Marinho</a>, <a href="/author/Hotho">A. Hotho</a>, <a href="/author/Jäschke">R. Jäschke</a>, <a href="/author/Nanopoulos">A. Nanopoulos</a>, <a href="/author/Rendle">S. Rendle</a>, <a href="/author/Schmidt-Thieme">L. Schmidt-Thieme</a>, <a href="/author/Stumme">G. Stumme</a>, and <a href="/author/Symeonidis">P. Symeonidis</a> </span><em>SpringerBriefs in Electrical and Computer Engineering </em><em>Springer, </em>(<em>February 2012</em>)Tue Feb 14 08:29:50 CET 2012febSpringerBriefs in Electrical and Computer EngineeringRecommender Systems for Social Tagging Systems20122012 bookmarking collaborative folksonomy myown recommender social tagging Social Tagging Systems are web applications in which users upload resources (e.g., bookmarks, videos, photos, etc.) and annotate it with a list of freely chosen keywords called tags. This is a grassroots approach to organize a site and help users to find the resources they are interested in. Social tagging systems are open and inherently social; features that have been proven to encourage participation. However, with the large popularity of these systems and the increasing amount of user-contributed content, information overload rapidly becomes an issue. Recommender Systems are well known applications for increasing the level of relevant content over the “noise” that continuously grows as more and more content becomes available online. In social tagging systems, however, we face new challenges. While in classic recommender systems the mode of recommendation is basically the resource, in social tagging systems there are three possible modes of recommendation: users, resources, or tags. Therefore suitable methods that properly exploit the different dimensions of social tagging systems data are needed. In this book, we survey the most recent and state-of-the-art work about a whole new generation of recommender systems built to serve social tagging systems. The book is divided into self-contained chapters covering the background material on social tagging systems and recommender systems to the more advanced techniques like the ones based on tensor factorization and graph-based models.http://www.bibsonomy.org/bibtex/2268e9546446d8bd65e0a15792879e333/folkefolke2012-02-14T00:56:20+01:00analysis entropy graph network theory <span class="authorEditorList"><a href="/author/Simonyi">G. Simonyi</a> </span><em>Combinatorial Optimization</em> (<em>1995</em>)Tue Feb 14 00:56:20 CET 2012Combinatorial Optimization399--441Graph entropy: A survey201995analysis entropy graph network theory http://www.bibsonomy.org/bibtex/27f9e0de989ed9bd4deaa41d39bc98d4c/folkefolke2012-02-14T00:53:13+01:00analysis entropy graph network theory <span class="authorEditorList"><a href="/author/Dehmer">M. Dehmer</a> </span><em>Applied Mathematics and Computation</em> <em>201(1):82--94</em> (<em>2008</em>)Tue Feb 14 00:53:13 CET 2012Applied Mathematics and Computation182--94Information processing in complex networks: Graph entropy and information functionals2012008analysis entropy graph network theory http://www.bibsonomy.org/bibtex/2000eaa395ab34d01885bf70fbd9cd1ac/beatebeate2012-02-13T23:20:51+01:00challenges spam spam-detection survey <span class="authorEditorList"><a href="/author/Fawcett">Tom Fawcett</a> </span><em>SIGKDD Explor. Newsl.</em> (<em>December 2003</em>)Mon Feb 13 23:20:51 CET 2012New York, NY, USASIGKDD Explor. Newsl.December140--148"In vivo" spam filtering: a challenge problem for KDD52003challenges spam spam-detection survey Spam, also known as Unsolicited Commercial Email (UCE), is the bane of email communication. Many data mining researchers have addressed the problem of detecting spam, generally by treating it as a static text classification problem. True <i>in vivo</i> spam filtering has characteristics that make it a rich and challenging domain for data mining. Indeed, real-world datasets with these characteristics are typically difficult to acquire and to share. This paper demonstrates some of these characteristics and argues that researchers should pursue <i>in vivo</i> spam filtering as an accessible domain for investigating them."In vivo" spam filteringhttp://www.bibsonomy.org/bibtex/2275220e7853ed9478bf88e804faf96a2/beatebeate2012-02-13T22:45:00+01:00ml naive-bayes spam spam-detection survey <span class="authorEditorList"><a href="/author/Guzella">Thiago S. Guzella</a>, and <a href="/author/Caminhas">Walmir M. Caminhas</a> </span><em>Expert Syst. Appl.</em> (<em>September 2009</em>)Mon Feb 13 22:45:00 CET 2012Tarrytown, NY, USAExpert Syst. Appl.September10206--10222Review: A review of machine learning approaches to Spam filtering362009ml naive-bayes spam spam-detection survey In this paper, we present a comprehensive review of recent developments in the application of machine learning algorithms to Spam filtering, focusing on both textual- and image-based approaches. Instead of considering Spam filtering as a standard classification problem, we highlight the importance of considering specific characteristics of the problem, especially concept drift, in designing new filters. Two particularly important aspects not widely recognized in the literature are discussed: the difficulties in updating a classifier based on the bag-of-words representation and a major difference between two early naive Bayes models. Overall, we conclude that while important advancements have been made in the last years, several aspects remain to be explored, especially under more realistic evaluation settings. Reviewhttp://www.bibsonomy.org/bibtex/287d6883ebd98e8810be45d7e7e4ade96/jaeschkejaeschke2012-02-13T12:52:23+01:002012 bookmarking collaborative folksonomy myown recommender social tagging <span class="authorEditorList"><a href="/author/Balby Marinho">L. Balby Marinho</a>, <a href="/author/Hotho">A. Hotho</a>, <a href="/author/Jäschke">R. Jäschke</a>, <a href="/author/Nanopoulos">A. Nanopoulos</a>, <a href="/author/Rendle">S. Rendle</a>, <a href="/author/Schmidt-Thieme">L. Schmidt-Thieme</a>, <a href="/author/Stumme">G. Stumme</a>, and <a href="/author/Symeonidis">P. Symeonidis</a> </span><em>SpringerBriefs in Electrical and Computer Engineering </em><em>Springer, </em>(<em>February 2012</em>)Mon Feb 13 12:52:23 CET 2012febSpringerBriefs in Electrical and Computer EngineeringRecommender Systems for Social Tagging Systems20122012 bookmarking collaborative folksonomy myown recommender social tagging Social Tagging Systems are web applications in which users upload resources (e.g., bookmarks, videos, photos, etc.) and annotate it with a list of freely chosen keywords called tags. This is a grassroots approach to organize a site and help users to find the resources they are interested in. Social tagging systems are open and inherently social; features that have been proven to encourage participation. However, with the large popularity of these systems and the increasing amount of user-contributed content, information overload rapidly becomes an issue. Recommender Systems are well known applications for increasing the level of relevant content over the “noise” that continuously grows as more and more content becomes available online. In social tagging systems, however, we face new challenges. While in classic recommender systems the mode of recommendation is basically the resource, in social tagging systems there are three possible modes of recommendation: users, resources, or tags. Therefore suitable methods that properly exploit the different dimensions of social tagging systems data are needed. In this book, we survey the most recent and state-of-the-art work about a whole new generation of recommender systems built to serve social tagging systems. The book is divided into self-contained chapters covering the background material on social tagging systems and recommender systems to the more advanced techniques like the ones based on tensor factorization and graph-based models.http://www.bibsonomy.org/bibtex/22055df95d68579ed8bad3b114b070deb/stummestumme2012-02-13T11:44:41+01:002012 ACM HT HT12 Hypertext SigWEB conferences <span class="authorEditorList"><a href="/author/Deshpande">Yogesh Deshpande</a> </span><em>SIGWEB Newsl.</em> (<em>January 2012</em>)Mon Feb 13 11:44:41 CET 2012New York, NY, USASIGWEB Newsl.janWinter7:1--7:10Up and coming SIGWEB supported conferences20122012 ACM HT HT12 Hypertext SigWEB conferences SIGWEB supports several specialized conferences, short courses, and workshops, as well as the Annual Hypertext Conference. SIGWEB sponsored conferences focus on timely topics in applied and computational hypertext and Web disciplines and provide a place for members and the entire applied Hypermedia and Web community to exchange ideas and to meet with and expand their network of colleagues. In this article, we provide a brief overview of SIGWEB sponsored conferences, in addition to events that are in cooperation with SIGWEB.Up and coming SIGWEB supported conferenceshttp://www.bibsonomy.org/bibtex/2d169c08d5241a0912f3d60c97d87e2c0/hothohotho2012-02-12T10:50:22+01:00analysis emotions sentiment toread <span class="authorEditorList"><a href="/author/Kim">Seungyeon Kim</a>, <a href="/author/Li">Fuxin Li</a>, <a href="/author/Lebanon">Guy Lebanon</a>, and <a href="/author/Essa">Irfan Essa</a> </span>(<em>2012</em>)<em>cite arxiv:1202.1568Comment: 15 pages, 7 figures . </em>Sun Feb 12 10:50:22 CET 2012cite arxiv:1202.1568Comment: 15 pages, 7 figuresBeyond Sentiment: The Manifold of Human Emotions2012analysis emotions sentiment toread Sentiment analysis predicts the presence of positive or negative emotions in a text document. In this paper we consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a finite set of human emotions. We investigate the resulting model, compare it to psychological observations, and explore its predictive capabilities. Besides obtaining significant improvements over a baseline without manifold, we are also able to visualize different notions of positive sentiment in different domains. Beyond Sentiment: The Manifold of Human Emotionshttp://www.bibsonomy.org/bibtex/24c2935e67765a5d2452b0ac24ee4ce3d/beatebeate2012-02-11T23:24:04+01:00social-search tagging toread <span class="authorEditorList"><a href="/author/Hsu">Ming-Hung Hsu</a>, and <a href="/author/Chen">Hsin-Hsi Chen</a> </span><em>Journal of the American Society for Information Science and Technology</em> (<em>2011</em>)Sat Feb 11 23:24:04 CET 2012Journal of the American Society for Information Science and Technologyn/aEfficient and effective prediction of social tags to enhance web search2011social-search tagging toread http://www.bibsonomy.org/bibtex/2bf63bc49139c80ed64d77fe279e1fe03/beatebeate2012-02-11T23:22:31+01:00comparison social-search tagging <span class="authorEditorList"><a href="/author/Razikin">Khasfariyati Razikin</a>, <a href="/author/Goh">Dion H. Goh</a>, <a href="/author/Chua">Alton Y. K. Chua</a>, and <a href="/author/Lee">Chei Sian Lee</a> </span><em>J. Inf. Sci.</em> (<em>August 2011</em>)Sat Feb 11 23:22:31 CET 2012Thousand Oaks, CA, USAJ. Inf. Sci.August391--404Social tags for resource discovery: a comparison between machine learning and user-centric approaches372011comparison social-search tagging http://www.bibsonomy.org/bibtex/27cbc93200945303e1415b320ac7b3715/beatebeate2012-02-11T23:18:18+01:00survey tagging <span class="authorEditorList"><a href="/author/Gupta">Manish Gupta</a>, <a href="/author/Li">Rui Li</a>, <a href="/author/Yin">Zhijun Yin</a>, and <a href="/author/Han">Jiawei Han</a> </span><em>SIGKDD Explor. Newsl.</em> (<em>November 2010</em>)Sat Feb 11 23:18:18 CET 2012New York, NY, USASIGKDD Explor. Newsl.November58--72Survey on social tagging techniques122010survey tagging Social tagging on online portals has become a trend now. It has emerged as one of the best ways of associating metadata with web objects. With the increase in the kinds of web objects becoming available, collaborative tagging of such objects is also developing along new dimensions. This popularity has led to a vast literature on social tagging. In this survey paper, we would like to summarize different techniques employed to study various aspects of tagging. Broadly, we would discuss about properties of tag streams, tagging models, tag semantics, generating recommendations using tags, visualizations of tags, applications of tags and problems associated with tagging usage. We would discuss topics like why people tag, what influences the choice of tags, how to model the tagging process, kinds of tags, different power laws observed in tagging domain, how tags are created, how to choose the right tags for recommendation, etc. We conclude with thoughts on future work in the area.Survey on social tagging techniqueshttp://www.bibsonomy.org/bibtex/26e66dae4e50f4a7c3ab3199456110840/beatebeate2012-02-11T23:12:17+01:00bookmark-weighting ranking recommender social-search <span class="authorEditorList"><a href="/author/Carmel">David Carmel</a>, <a href="/author/Roitman">Haggai Roitman</a>, and <a href="/author/Yom-Tov">Elad Yom-Tov</a> </span><em>The VLDB Journal</em> <em>19(6):761--775</em> (<em>December 2010</em>)Sat Feb 11 23:12:17 CET 2012Secaucus, NJ, USAThe VLDB Journaldec6761--775Social bookmark weighting for search and recommendation192010bookmark-weighting ranking recommender social-search Social bookmarking enables knowledge sharing and efficient discovery on the web, where users can collaborate together by tagging documents of interests. A lot of attention was given lately for utilizing social bookmarking data to enhance traditional IR tasks. Yet, much less attention was given to the problem of estimating the effectiveness of an individual bookmark for the specific tasks. In this work, we propose a novel framework for social bookmark weighting which allows us to estimate the effectiveness of each of the bookmarks individually for several IR tasks. We show that by weighting bookmarks according to their estimated quality, we can significantly improve social search effectiveness. We further demonstrate that using the same framework, we can derive solutions to several recommendation tasks such as tag recommendation, user recommendation, and document recommendation. Empirical evaluation on real data gathered from two large bookmarking systems demonstrates the effectiveness of the new social bookmark weighting framework.Social bookmark weighting for search and recommendationhttp://www.bibsonomy.org/bibtex/26cd42f4b457fed4f6d2eee51b6b0232b/beatebeate2012-02-11T22:51:37+01:00case-study metadata social-search tagging youtube <span class="authorEditorList"><a href="/author/Jeong">Wooseob Jeong</a> </span><em>Proceedings of the 2009 International Conference on Dublin Core and Metadata Applications, </em><em>page 31--39. </em><em>Dublin Core Metadata Initiative, </em>(<em>2009</em>)Sat Feb 11 22:51:37 CET 2012Proceedings of the 2009 International Conference on Dublin Core and Metadata Applications31--39Is tagging effective?: overlapping ratios with other metadata fields2009case-study metadata social-search tagging youtube The potential advantages of tagging have been addressed in numerous literatures, however still the effectiveness of tagging in information retrieval has not confirmed yet along with continuous intensive debates between advocates of new tagging systems versus traditional controlled vocabulary metadata. Despite all the potential advantages of tagging, the overlapping ratios between tags and the words used in other metadata fields, such as title and description, are significant. In this study, with the data from Youtube.com videos, the degree of overlapping is examined among the fields of title, description and tag, with additional questions about tagging, such as changes in numbers of words in each metadata field over time and the difference between web site promotion videos and non-promotion videos. The findings include 1) the number of words in each metadata fields have increased over time; 2) web site promotional videos have more words in each metadata fields than non-promotional videos; 3) more than 50% of words are shared among metadata fields including the tag field; 4) as much as 25% of the videos have the exactly same words repeated among the metadata fields. More similar studies with data from other social tagging sites are suggested to verify these findings.Is tagging effective?http://www.bibsonomy.org/bibtex/2eb4af45f7872ffe54dd9d735a8738f77/beatebeate2012-02-11T19:59:48+01:00ranking social-search tagging toread <span class="authorEditorList"><a href="/author/Sarkas">Nikos Sarkas</a>, <a href="/author/Das">Gautam Das</a>, and <a href="/author/Koudas">Nick Koudas</a> </span><em>Proc. VLDB Endow.</em> (<em>August 2009</em>)Sat Feb 11 19:59:48 CET 2012Proc. VLDB Endow.August778--789Improved search for socially annotated data22009ranking social-search tagging toread Social annotation is an intuitive, on-line, collaborative process through which each element of a collection of resources (e.g., URLs, pictures, videos, etc.) is associated with a group of descriptive keywords, widely known as tags. Each such group is a concise and accurate summary of the relevant resource's content and is obtained via aggregating the opinion of individual users, as expressed in the form of short tag sequences. The availability of this information gives rise to a new searching paradigm where resources are retrieved and ranked based on the similarity of a keyword query to their accompanying tags.</p> <p>In this paper, we present a principled and efficient search and resource ranking methodology that utilizes exclusively the user-assigned tag sequences. Ranking is based on solid probabilistic foundations and our growing understanding of the dynamics and structure of the social annotation process, which we capture by employing powerful interpolated <i>n</i>-gram models on the tag sequences. The efficiency and applicability of the proposed solution to large data sets is guaranteed through the introduction of a novel and highly scalable constrained optimization framework, employed both for training and incrementally maintaining the <i>n</i>-gram models.</p> <p>We experimentally validate the efficiency and effectiveness of our solutions compared to other applicable approaches. Our evaluation is based on a large crawl of del.icio.us, numbering hundreds of thousands of users and millions of resources, thus demonstrating the applicability of our solutions to real-life, large scale systems. In particular, we demonstrate that the use of interpolated <i>n</i>-grams for modeling tag sequences results in superior ranking effectiveness, while the proposed optimization framework is superior in terms of performance both for obtaining ranking parameters and incrementally maintaining them.Improved search for socially annotated datahttp://www.bibsonomy.org/bibtex/2c4132068f58570d46fbaa09d374e7a84/beatebeate2012-02-11T19:51:29+01:00case-study social-search tagging <span class="authorEditorList"><a href="/author/Bischoff">Kerstin Bischoff</a>, <a href="/author/Firan">Claudiu S. Firan</a>, <a href="/author/Nejdl">Wolfgang Nejdl</a>, and <a href="/author/Paiu">Raluca Paiu</a> </span><em>Proceedings of the 17th ACM conference on Information and knowledge management, </em><em>page 193--202. </em><em>New York, NY, USA, </em><em>ACM, </em>(<em>2008</em>)Sat Feb 11 19:51:29 CET 2012New York, NY, USAProceedings of the 17th ACM conference on Information and knowledge management193--202CIKM '08Can all tags be used for search?2008case-study social-search tagging Collaborative tagging has become an increasingly popular means for sharing and organizing Web resources, leading to a huge amount of user generated metadata. These tags represent quite a few different aspects of the resources they describe and it is not obvious whether and how these tags or subsets of them can be used for search. This paper is the first to present an in-depth study of tagging behavior for very different kinds of resources and systems - Web pages (Del.icio.us), music (Last.fm), and images (Flickr) - and compares the results with anchor text characteristics. We analyze and classify sample tags from these systems, to get an insight into what kinds of tags are used for different resources, and provide statistics on tag distributions in all three tagging environments. Since even relevant tags may not add new information to the search procedure, we also check overlap of tags with content, with metadata assigned by experts and from other sources. We discuss the potential of different kinds of tags for improving search, comparing them with user queries posted to search engines as well as through a user survey. The results are promising and provide more insight into both the use of different kinds of tags for improving search and possible extensions of tagging systems to support the creation of potentially search-relevant tags.Can all tags be used for search?http://www.bibsonomy.org/bibtex/2c97aa592f078df006bda79133fedfd98/macekmacek2012-02-11T15:16:12+01:00HTAnatomy <span class="authorEditorList"><a href="/author/Isella">Lorenzo Isella</a>, <a href="/author/Romano">M. Romano</a>, <a href="/author/Barrat">Alain Barrat</a>, <a href="/author/Cattuto">Ciro Cattuto</a>, <a href="/author/Colizza">Vittoria Colizza</a>, <a href="/author/den Broeck">Wouter Van den Broeck</a>, <a href="/author/Gesualdo">F. Gesualdo</a>, <a href="/author/Pandolfi">E. Pandolfi</a>, <a href="/author/Ravà">L. Ravà</a>, <a href="/author/Rizzo">Caterina Rizzo</a>, and <a href="/author/Tozzi">Alberto E. Tozzi</a> </span><em>CoRR</em> (<em>2011</em>)Sat Feb 11 15:16:12 CET 2012CoRRClose encounters in a pediatric ward: measuring face-to-face proximity and mixing patterns with wearable sensorsabs/1104.25152011HTAnatomy analyzing contacts between different groups of clinic personal in order to measure dynamics of infection transmission in a hospitalhttp://www.bibsonomy.org/bibtex/22fc889495ce1b0f702080dfd2d30e44a/macekmacek2012-02-11T15:10:18+01:00HTAnatomy <span class="authorEditorList"><a href="/author/Stehlé">Juliette Stehlé</a>, <a href="/author/Voirin">N. Voirin</a>, <a href="/author/Barrat">Alain Barrat</a>, <a href="/author/Cattuto">Ciro Cattuto</a>, <a href="/author/Isella">Lorenzo Isella</a>, <a href="/author/Pinton">Jean-François Pinton</a>, <a href="/author/Quaggiotto">M. Quaggiotto</a>, <a href="/author/den Broeck">Wouter Van den Broeck</a>, <a href="/author/Régis">C. Régis</a>, <a href="/author/Lina">B. Lina</a>, and <a href="/author/Vanhems">P. Vanhems</a> </span><em>CoRR</em> (<em>2011</em>)Sat Feb 11 15:10:18 CET 2012CoRRHigh-resolution measurements of face-to-face contact patterns in a primary schoolabs/1109.10152011HTAnatomy time series analysis of node degree and contact length using sliding windowshttp://www.bibsonomy.org/bibtex/267828c144ffab3b811202f99ce082e7e/macekmacek2012-02-11T14:59:42+01:00HTAnatomy <span class="authorEditorList"><a href="/author/McPherson">Miller McPherson</a>, <a href="/author/Smith-Lovin">Lynn Smith-Lovin</a>, and <a href="/author/Cook">James M. Cook</a> </span><em>Annu. Rev. Sociol.</em> <em>27(1):415--444</em> (<em>2001</em>)Sat Feb 11 14:59:42 CET 2012Annu. Rev. Sociol.1415--444Birds of a Feather: Homophily in Social Networks272001HTAnatomy Similarity breeds connection. This principle—the homophily principle—structures network ties of every type, including marriage, friendship, work, advice, support, information transfer, exchange, comembership, and other types of relationship. The result is that people's personal networks are homogeneous with regard to many sociodemographic, behavioral, and intrapersonal characteristics. Homophily limits people's social worlds in a way that has powerful implications for the information they receive, the attitudes they form, and the interactions they experience. Homophily in race and ethnicity creates the strongest divides in our personal environments, with age, religion, education, occupation, and gender following in roughly that order. Geographic propinquity, families, organizations, and isomorphic positions in social systems all create contexts in which homophilous relations form. Ties between nonsimilar individuals also dissolve at a higher rate, which sets the stage for the formation of niches (localized positions) within social space. We argue for more research on: (a) the basic ecological processes that link organizations, associations, cultural communities, social movements, and many other social forms; (b) the impact of multiplex ties on the patterns of homophily; and (c) the dynamics of network change over time through which networks and other social entities co-evolve.http://www.bibsonomy.org/bibtex/23bd44a9ed5aea1f48006f0b2af4f4fc0/macekmacek2012-02-11T14:44:01+01:00HTAnatomy <span class="authorEditorList"><a href="/author/Barrat">Alain Barrat</a>, <a href="/author/Cattuto">Ciro Cattuto</a>, <a href="/author/Szomszor">Martin Szomszor</a>, <a href="/author/den Broeck">Wouter Van den Broeck</a>, and <a href="/author/Alani">Harith Alani</a> </span><em>International Semantic Web Conference 2, </em><em>volume 6497 of Lecture Notes in Computer Science, </em><em>page 17-33. </em><em>Springer, </em>(<em>2010</em>)Sat Feb 11 14:44:01 CET 2012International Semantic Web Conference (2)conf/semweb/2010-217-33Lecture Notes in Computer ScienceSocial Dynamics in Conferences: Analyses of Data from the Live Social Semantics Application.64972010HTAnatomy seniority of the neighbours, contact length distributions, web2.0 activity, comparison of those measures for several conferences,http://www.bibsonomy.org/bibtex/28eb3850df53262492c16071ee9cbb911/beatebeate2012-02-11T12:00:44+01:00classification social-search tagging <span class="authorEditorList"><a href="/author/Au Yeung">Ching Man Au Yeung</a>, <a href="/author/Gibbins">Nicholas Gibbins</a>, and <a href="/author/Shadbolt">Nigel Shadbolt</a> </span><em>Proceedings of the Workshop on Exploiting Semantic Annotations in Information Retrieval ESAIR 2008, co-located with ECIR 2008, Glasgow, United Kingdom, 31 March, 2008, </em><em>page 48--61. </em>(<em>2008</em>)Sat Feb 11 12:00:44 CET 2012Proceedings of the Workshop on Exploiting Semantic Annotations in Information Retrieval (ESAIR 2008), co-located with ECIR 2008, Glasgow, United Kingdom, 31 March, 200848--61Web Search Disambiguation by Collaborative Tagging2008classification social-search tagging Existing Web search engines such as Google mostly adopt a keyword-based approach, which matches the keywords in a query sub- mitted by a user with the keywords characterising the indexed Web doc- uments, and is quite successful in general in helping users locate useful documents. However, when the keyword submitted by the user is am- biguous, the search result usually consists of documents related to var- ious meanings of the keyword, in which probably only one of them is interesting to the user. In this paper we attempt to provide a solution to this problem by using the semantics extracted from collaborative tag- ging in the social bookmarking site del.icio.us. For an ambiguous word, we extract sets of tags which are related to it in di®erent contexts by performing a community-discovery algorithm on folksonomy networks. The sets of tags are then used to disambiguate search results returned by del.icio.us and Google. Experimental results show that our method is able to disambiguate the documents returned by the two systems with high precision.