@article{keyhere, title = {The Intention Behind Web Queries}, author = {Ricardo Baeza-Yates and Liliana Calderón-Benavides and Cristina González-Caro}, journal = {String Processing and Information Retrieval}, pages = {98--109}, year = 2006, url = {http://dx.doi.org/10.1007/11880561_9}, description = {SpringerLink - Buchkapitel}, abstract = {The identification of the user’s intention or interest through queries that they submit to a search engine can be very useful to offer them more adequate results. In this work we present a framework for the identification of user’s interest in an automaticway, based on the analysis of query logs. This identification is made from two perspectives, the objectives or goals of auser and the categories in which these aims are situated. A manual classification of the queries was made in order to havea reference point and then we applied supervised and unsupervised learning techniques. The results obtained show that fora considerable amount of cases supervised learning is a good option, however through unsupervised learning we found relationshipsbetween users and behaviors that are not easy to detect just taking the query words. Also, through unsupervised learning weestablished that there are categories that we are not able to determine in contrast with other classes that were not consideredbut naturally appear after the clustering process. This allowed us to establish that the combination of supervised and unsupervisedlearning is a good alternative to find user’s goals. From supervised learning we can identify the user interest given certainestablished goals and categories; on the other hand, with unsupervised learning we can validate the goals and categories used,refine them and select the most appropriate to the user’s needs.}, biburl = {http://www.bibsonomy.org/bibtex/227c7357d3337d890fef53168dce9ed33/hotho}, keywords = {intention search query dm toread analysis ml} } @article{1377474, title = {Tagging and searching: Search retrieval effectiveness of folksonomies on the World Wide Web}, address = {Tarrytown, NY, USA}, author = {P. Jason Morrison}, journal = {Inf. Process. Manage.}, number = 4, pages = {1562--1579}, publisher = {Pergamon Press, Inc.}, volume = 44, year = 2008, url = {http://portal.acm.org/citation.cfm?id=1377474}, issn = {0306-4573}, doi = {http://dx.doi.org/10.1016/j.ipm.2007.12.010}, description = {Tagging and searching}, abstract = {Many Web sites have begun allowing users to submit items to a collection and tag them with keywords. The folksonomies built from these tags are an interesting topic that has seen little empirical research. This study compared the search information retrieval (IR) performance of folksonomies from social bookmarking Web sites against search engines and subject directories. Thirty-four participants created 103 queries for various information needs. Results from each IR system were collected and participants judged relevance. Folksonomy search results overlapped with those from the other systems, and documents found by both search engines and folksonomies were significantly more likely to be judged relevant than those returned by any single IR system type. The search engines in the study had the highest precision and recall, but the folksonomies fared surprisingly well. Del.icio.us was statistically indistinguishable from the directories in many cases. Overall the directories were more precise than the folksonomies but they had similar recall scores. Better query handling may enhance folksonomy IR performance further. The folksonomies studied were promising, and may be able to improve Web search performance.}, biburl = {http://www.bibsonomy.org/bibtex/27e1dc3f52085093cc33d8fe931253b34/hotho}, keywords = {ir comparision search engine performance retrieval folksonomy toread} } @inproceedings{Noll/2007/search, title = {Web search personalization via social bookmarking and tagging}, address = {Berlin, Heidelberg}, author = {Michael Noll and Christoph Meinel}, booktitle = {Proceedings of the 6th International Semantic Web Conference and 2nd Asian Semantic Web Conference (ISWC/ASWC2007), Busan, South Korea}, crossref = {http://data.semanticweb.org/conference/iswc-aswc/2007/proceedings}, editor = {Karl Aberer and Key-Sun Choi and Natasha Noy and Dean Allemang and Kyung-Il Lee and Lyndon J B Nixon and Jennifer Golbeck and Peter Mika and Diana Maynard and Guus Schreiber and Philippe Cudré-Mauroux}, month = {November}, pages = {365--378}, publisher = {Springer Verlag}, series = {LNCS}, volume = 4825, year = 2007, url = {http://iswc2007.semanticweb.org/papers/365.pdf}, abstract = {In this paper, we present a new approach to web search personalization based on user collaboration and sharing of information about web documents. The proposed personalization technique separates data collection and user profiling from the information system whose contents and indexed documents are being searched for, i.e. the search engines, and uses social bookmarking and tagging to re-rank web search results. It is independent of the search engine being used, so users are free to choose the one they prefer, even if their favorite search engine does not natively support personalization. We show how to design and implement such a system in practice and investigate its feasibility and usefulness with large sets of real-word data and a user study.}, biburl = {http://www.bibsonomy.org/bibtex/252943a6298169f5a552bffbbee352937/hotho}, keywords = {iswc bookmarking tagging search social toread} } @inproceedings{krause2008comparison, title = {A Comparison of Social Bookmarking with Traditional Search}, author = {Beate Krause and Andreas Hotho and Gerd Stumme}, booktitle = {Advances in Information Retrieval, 30th European Conference on IR Research, ECIR 2008}, pages = {101-113}, publisher = {Springer}, volume = 4956, year = 2008, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2008/ecir2008krause.pdf}, abstract = {Social bookmarking systems allow users to store links to internet resources on a web page. As social bookmarking systems are growing in popularity, search algorithms have been developed that transfer the idea of link-based rankings in the Web to a social bookmarking system’s data structure. These rankings differ from traditional search engine rankings in that they incorporate the rating of users. In this study, we compare search in social bookmarking systems with traditionalWeb search. In the first part, we compare the user activity and behaviour in both kinds of systems, as well as the overlap of the underlying sets of URLs. In the second part,we compare graph-based and vector space rankings for social bookmarking systems with commercial search engine rankings. Our experiments are performed on data of the social bookmarking system Del.icio.us and on rankings and log data from Google, MSN, and AOL. We will show that part of the difference between the systems is due to different behaviour (e. g., the concatenation of multi-word lexems to single terms in Del.icio.us), and that real-world events may trigger similar behaviour in both kinds of systems. We will also show that a graph-based ranking approach on folksonomies yields results that are closer to the rankings of the commercial search engines than vector space retrieval, and that the correlation is high in particular for the domains that are well covered by the social bookmarking system.}, biburl = {http://www.bibsonomy.org/bibtex/2613f5c41ff759fc548c9085102d1c933/hotho}, keywords = {2008 bookmarking search social query myown log} } @inproceedings{Jaeschke2008logsonomy, title = {Logsonomy — A Search Engine Folksonomy}, author = {Robert Jäschke and Beate Krause and Andreas Hotho and Gerd Stumme}, booktitle = {Proceedings of the Second International Conference on Weblogs and Social Media(ICWSM 2008)}, publisher = {AAAI Press}, year = 2008, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2008/Krause2008logsonomy_short.pdf}, abstract = {In social bookmarking 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. Search engines filter the vast information of the web. Queries 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. The clickdata can be represented as a folksonomy in which queries are descriptions of clicked URLs. This poster analyzes the topological characteristics of the resulting tripartite hypergraph of queries, users and bookmarks of two query logs and compares it two a snapshot of the folksonomy del.icio.us.}, biburl = {http://www.bibsonomy.org/bibtex/2359e1eccdc524334d4a2ad51330f76ae/hotho}, keywords = {2008 search query logsonomy myown icwsm folksonomy analysis log network} } @article{10.1109/WI.2007.108, title = {Using PersonalizedWeb Search for Enhancing Common Sense and Folksonomy Based Intelligent Search Systems}, address = {Los Alamitos, CA, USA}, author = {Mohammad Nauman and Shahbaz Khan}, journal = {wi}, pages = {423-426}, publisher = {IEEE Computer Society}, volume = 0, year = 2007, isbn = {0-7695-3026-5}, doi = {http://doi.ieeecomputersociety.org/10.1109/WI.2007.108}, description = {Using PersonalizedWeb Search for Enhancing Common Sense and Folksonomy Based Intelligent Search Systems}, biburl = {http://www.bibsonomy.org/bibtex/2799817443dab31b534315a790c24a9f6/hotho}, keywords = {search summerschool folksonomy ranking kdubiq} } @article{sinclair:ftc, title = {{The folksonomy tag cloud: When is it useful?}}, author = {J. Sinclair and M. Cardew-Hall}, journal = {Journal of Information Science}, pages = {016555150607808}, publisher = {CILIP}, year = 2007, biburl = {http://www.bibsonomy.org/bibtex/2539fe40eb8dd2597956cae27d6fb02ac/hotho}, keywords = {tagging search tag summerschool cloud folksonomy ranking kdubiq} } @inproceedings{hotho2006information, title = {Information Retrieval in Folksonomies: Search and Ranking}, address = {Budva, Montenegro}, author = {Andreas Hotho and Robert Jäschke and Christoph Schmitz and Gerd Stumme}, booktitle = {Proceedings of the 3rd European Semantic Web Conference }, month = {June}, pages = {411-426}, publisher = {Springer}, series = {LNCS}, volume = 4011, year = 2006, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/seach2006hotho_eswc.pdf}, isbn = {3-540-34544-2}, vgwort = {29}, biburl = {http://www.bibsonomy.org/bibtex/27da1127fc4836e2cf58e3073f1b888b2/hotho}, keywords = {ir 2006 definition pagerank seminar2006 summerschool bibsonomy myown rank search folksonomy folkrank sosbuch ranking kdubiq} } @article{bloehdorn2006intro, title = {Introduction to the Special Issue 'Learning in Web Search'}, author = {S. Bloehdorn and W. Buntine and A. Hotho}, editor = {S. Bloehdorn and W. Buntine and A. Hotho}, institution = {An International Journal of Computing and Informatics}, journal = {Informatica}, number = 2, pages = {141-141}, volume = 30, year = 2006, url = {http://www.informatica.si/PDF/30-2/00_Introduction.pdf}, issn = {0350-5596}, date = {(2006)}, biburl = {http://www.bibsonomy.org/bibtex/2e434232b8e3b80ff3b95006432fe54ee/hotho}, keywords = {ir 2006 search web ml} } @proceedings{2005-lws-proceedings, title = {Proceedings of the Workshop on Learning in Web Search (LWS 2005) }, editor = {Stephan Bloehdorn and Wray Buntine and Andreas Hotho}, month = {AUG}, note = {Workshop at the 22nd International Conference on Machine Learning (ICML 2005) }, year = 2005, url = {http://cosco.hiit.fi/search/learninginsearch05/ICML_W4.pdf}, biburl = {http://www.bibsonomy.org/bibtex/22de98c2b635f36c137e25256e8c235e0/hotho}, keywords = {ir search 2005 web myown ml} } @article{kleinberg1999hits, title = {Authoritative sources in a hyperlinked environment}, author = {Jon M. Kleinberg}, journal = {Journal of the ACM}, number = 5, pages = {604--632}, volume = 46, year = 1999, url = {http://citeseer.ist.psu.edu/kleinberg99authoritative.html}, id = {1115}, priority = {1}, comment = {HITS algorithm}, abstract = {. The network structure of a hyperlinked environment can be a rich source of information about the content of the environment, provided we have effective means for understanding it. We develop a set of algorithmic tools for extracting information from the link structures of such environments, and report on experiments that demonstrate their effectiveness in a variety of contexts on the World Wide Web. The central issue we address within our framework is the distillation of broad search topics,...}, biburl = {http://www.bibsonomy.org/bibtex/2c86549355475331f563d0a3ba7816dab/hotho}, keywords = {hits search sosbuch ranking} } @inproceedings{Pageetal98, title = {The PageRank citation ranking: Bringing order to the Web}, address = {Brisbane, Australia}, author = {L. Page and S. Brin and R. Motwani and T. Winograd}, booktitle = {Proceedings of the 7th International World Wide Web Conference}, pages = {161--172}, year = 1998, url = {citeseer.nj.nec.com/page98pagerank.html}, biburl = {http://www.bibsonomy.org/bibtex/2ac49c33e114ca171db40cece6a0ae4d6/hotho}, keywords = {pagerank search sosbuch ranking} } @article{keyhere, title = {Syntactic clustering of the Web}, author = {Andrei Z. Broder and Steven C. Glassman and Mark S. Manasse and Geoffrey Zweig}, booktitle = {Papers from the Sixth International World Wide Web Conference}, journal = {Computer Networks and ISDN Systems}, month = {#sep#}, number = {8-13}, pages = {1157--1166}, volume = 29, year = 1997, url = {http://www.sciencedirect.com/science/article/B6TYT-3SP60S4-11/2/38f44c816ec8d69b406317de1629e56d}, description = {ScienceDirect - Computer Networks and ISDN Systems : Syntactic clustering of the Web}, abstract = {We have developed an efficient way to determine the syntactic similarity of files and have applied it to every document on the World Wide Web. Using this mechanism, we built a clustering of all the documents that are syntactically similar. Possible applications include a "Lost and Found" service, filtering the results of Web searches, updating widely distributed web-pages, and identifying violations of intellectual property rights.}, biburl = {http://www.bibsonomy.org/bibtex/293a3440b81c13ec81c17481a97719c71/hotho}, keywords = {search Web Resemblance Duplication Signatures Similarity Fingerprints} } @inproceedings{breese98empirical, title = {Empirical Analysis of Predictive Algorithms for Collaborative Filtering}, author = {John S. Breese and David Heckerman and Carl Kadie}, booktitle = {Proceedings of the 14$^{th}$ Conference on Uncertainty in Artificial Intelligence}, pages = {43-52}, year = 1998, biburl = {http://www.bibsonomy.org/bibtex/282cd7b6c312f4181b1d05adb10c1d56a/hotho}, keywords = {comparision collaborative search filtering recommender toread ranking} } @article{fensel2007, title = {Unifying Reasoning and Search to Web Scale}, author = {Dieter Fensel and Frank Van Harmelen}, journal = {IEEE Internet Computing}, month = {March/April}, number = 2, pages = {94--96}, volume = 11, year = 2007, url = {http://www.cs.vu.nl/~frankh/postscript/IEEE-IC07.pdf}, description = {Unifying Reasoning and Search to Web Scale}, biburl = {http://www.bibsonomy.org/bibtex/21d7ac4bf2a12a9e0420dd0e03c36d518/hotho}, keywords = {scale search semantic web toread} } @article{crestani1997spreading, title = {Application of Spreading Activation Techniques in Information Retrieval}, author = {F. Crestani}, journal = {Artificial Intelligence Review}, month = {December}, number = 6, pages = {453--482}, volume = 11, year = 1997, url = {http://dx.doi.org/10.1023/A:1006569829653}, description = {SpringerLink - Zeitschriftenbeitrag}, abstract = {This paper surveys the use of Spreading Activation techniques onSemantic Networks in Associative Information Retrieval. The majorSpreading Activation models are presented and their applications toIR is surveyed. A number of works in this area are criticallyanalyzed in order to study the relevance of Spreading Activation forassociative IR. ER -}, biburl = {http://www.bibsonomy.org/bibtex/2c26c16e0a8036000b788fada656f59dd/hotho}, keywords = {ir information msn spreading search survey semantic retrieval *** network activation} } @inproceedings{HWLK06, title = {Substitution or Complement: An Empirical Analysis on the Impact of Collaborative Tagging on Web Search.}, author = {Peng Han and Zhimei Wang and Zhiyun Li and Bernd Kramer and Fan Yang}, booktitle = {Web Intelligence}, crossref = {conf/webi/2006}, pages = {757-760}, publisher = {IEEE Computer Society}, year = 2006, url = {http://dblp.uni-trier.de/db/conf/webi/webi2006.html#HanWLKY06}, ee = {http://doi.ieeecomputersociety.org/10.1109/WI.2006.162}, isbn = {0-7695-2747-7}, date = {2007-01-10}, biburl = {http://www.bibsonomy.org/bibtex/2b652b0d73b964ebc282c3c3060c01c9d/hotho}, keywords = {tagging search folksonomy ***} } @misc{web2006witten, title = {Web Dragons: Inside the Myths of Search Engine Technology }, author = {Ian Witten and Marco Gori and Teresa Numerico}, year = 2006, isbn = {0-12-370609-2}, biburl = {http://www.bibsonomy.org/bibtex/226dd2b2627dc5ee6100840328e0c20f0/hotho}, keywords = {mining search web toread} } @inproceedings{conf/ausai/YooH03, title = {A New Approach for Concept-Based Web Search.}, author = {Seung Yeol Yoo and Achim G. Hoffmann}, booktitle = {Australian Conference on Artificial Intelligence}, pages = {65-76}, year = 2003, url = {http://dblp.uni-trier.de/db/conf/ausai/ausai2003.html#YooH03}, ee = {http://springerlink.metapress.com/openurl.asp?genre=article&issn=0302-9743&volume=2903&spage=65}, biburl = {http://www.bibsonomy.org/bibtex/2897fb5d2ab04ccbd613b9574fd4c9e47/hotho}, keywords = {search classification web taxonomy comparison fca} } @inproceedings{conf/vldb/GyongyiGP04, title = {Combating Web Spam with TrustRank.}, author = {Zoltán Gyöngyi and Hector Garcia-Molina and Jan Pedersen}, booktitle = {VLDB}, pages = {576-587}, year = 2004, url = {http://dblp.uni-trier.de/db/conf/vldb/vldb2004.html#GyongyiGP04}, ee = {http://www.vldb.org/conf/2004/RS15P3.PDF}, biburl = {http://www.bibsonomy.org/bibtex/20d15cc263e9ca534e79c2d6f470f725e/hotho}, keywords = {rank search trust social web spam network} }