@inbook{burghardt2012searching, abstract = {Purpose — This chapter illustrates and explains the ambiguity and vagueness of the term social search and aims at describing and classifying the heterogeneous landscape of social search implementations on the WWW. Methodology/approach — We have looked at different definitions as well as the context of social search by carrying out an extensive literature review, and tried to unify and enhance existing ideas and concepts. Our definition of social search is illustrated by a general review of existing social search engines, which are analyzed and described by their specific features and social aspects. Findings — The chapter presents a discussion of social search as well as a comparison of existing social search engines. Social implications — The definition of social search and the comparison of social search engines summarize the many ways people can search the web together and allow for an assessment of future developments in this area. Originality/value of paper — Although different attempts to define social search have been made in the past, we present an argumentation that unifies some existing definitions and which is different from other interpretations of the social search concept. We present an overview and a comparison of the different genres of social search engines.}, author = {Burghardt, Manuel and Heckner, Markus and Wolff, Christian}, booktitle = {Web Search Engine Research}, chapter = 2, dopi = {10.1108/S1876-0562(2012)002012a004}, editor = {Lewandowski, Dirk}, interhash = {760d490f06ff6b70560bb1dd63413ecd}, intrahash = {b4df78513e065c66d9f1812026e5fff4}, isbn = {978-1-78052-636-2}, pages = {19--46}, publisher = {Emerald Group Publishing Limited}, series = {Library and Information Science}, title = {The Many Ways of Searching the Web Together: A Comparison of Social Search Engines}, url = {http://www.emeraldinsight.com/books.htm?chapterid=17030444}, volume = 4, year = 2012 } @inproceedings{benczur2008survey, abstract = {While Web archive quality is endangered by Web spam, a side effect of the high commercial value of top-ranked search-engine results, so farWeb spam filtering technologies are rarely used byWeb archivists. In this paper we make the first attempt to disseminate existing methodology and envision a solution for Web archives to share knowledge and unite efforts in Web spam hunting. We survey the state of the art inWeb spam filtering illustrated by the recent Web spam challenge data sets and techniques and describe the filtering solution for archives envisioned in the LiWA—Living Web Archives project.}, address = {Aaarhus, Denmark}, author = {Benczúr, András A. and Siklósi, Dávid and Szabó, Jácint and Bíró, István and Fekete, Zsolt and and Miklós Kurucz and Pereszlényi, Attila and Rácz, Simon and Szabó, Adrienn}, booktitle = {Proceedings of the 8th International Web Archiving Workshop IWAW'08}, interhash = {b09d09a4d29ba2a80a5a29b9a76ed5f0}, intrahash = {911a912a75e50451923522223f7717e8}, month = sep, title = {Web Spam: a Survey with Vision for the Archivist}, url = {http://iwaw.europarchive.org/08/IWAW2008-Benczur.pdf}, year = 2008 } @article{jws2006Semantic, abstract = {SemanticWeb Mining aims at combining the two fast-developing research areas SemanticWeb andWeb Mining. This survey analyzes the convergence of trends from both areas: an increasing number of researchers is working on improving the results ofWeb Mining by exploiting semantic structures in theWeb, and they make use ofWeb Mining techniques for building the Semantic Web. Last but not least, these techniques can be used for mining the Semantic Web itself. The Semantic Web is the second-generation WWW, enriched by machine-processable information which supports the user in his tasks. Given the enormous size even of today’s Web, it is impossible to manually enrich all of these resources. Therefore, automated schemes for learning the relevant information are increasingly being used. Web Mining aims at discovering insights about the meaning of Web resources and their usage. Given the primarily syntactical nature of the data being mined, the discovery of meaning is impossible based on these data only. Therefore, formalizations of the semantics of Web sites and navigation behavior are becoming more and more common. Furthermore, mining the Semantic Web itself is another upcoming application. We argue that the two areas Web Mining and Semantic Web need each other to fulfill their goals, but that the full potential of this convergence is not yet realized. This paper gives an overview of where the two areas meet today, and sketches ways of how a closer integration could be profitable.}, author = {Stumme, Gerd and Hotho, Andreas and Berendt, Bettina}, interhash = {3fd4efcf649ab35e8ef001f19b7ff83c}, intrahash = {9937253e6b2591267a0596fa597a4b96}, journal = {Journal of Web Semantics}, number = 2, pages = {124-143}, publisher = {Elsevier}, title = {Semantic Web Mining - State of the Art and Future Directions}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/stumme2006semantic.pdf}, volume = 4, year = 2006 } @article{langville2004deeper, abstract = {This paper serves as a companion or extension to the "Inside PageRank" paper by Bianchini et al. [Bianchini et al. 03]. It is a comprehensive survey of all issues associated with PageRank, covering the basic PageRank model, available and recommended solution methods, storage issues, existence, uniqueness, and convergence properties, possible alterations to the basic model, suggested alternatives to the traditional solution methods, sensitivity and conditioning, and finally the updating problem. We introduce a few new results, provide an extensive reference list, and speculate about exciting areas of future research.}, author = {Langville, Amy N. and Meyer, Carl D.}, interhash = {ee90e6dabf6645028ff3905a6fea3356}, intrahash = {6f7e377aad77931106f38284f107de8d}, issn = {1542-7951}, journal = {Internet Mathematics}, number = 3, pages = {335--380}, title = {Deeper inside {P}age{R}ank}, url = {http://akpeters.metapress.com/content/bn22r01j43g6q8g6/?p=9ef70461930f4e6dbf734cf7ca4cf9f2&pi=3}, volume = 1, year = 2004 } @article{golbeck2006trust, abstract = {The success of the Web is based largely on its open, decentralized nature; at the same time, that allows for a wide range of perspectives and intentions. Trust is required to foster successful interactions and to filter the abundance of information. In this review, we present a comprehensive survey of trust on the Web in all its contexts. Three main targets of trust are identified: content, services, and people. Trust in the content on the Web, including webpages, websites, and Semantic Web data is addressed first. Then, we move on to look at services including peer-to-peer environments and Web services. This includes a discussion of Web policy frameworks for access control. People are the final group, where we look at the role of trust in web-based social networks and algorithms for inferring trust relationships. Finally, we review applications that rely on trust and address how they utilize trust to improve functionality and interface. }, address = {Hanover, MA, USA}, author = {Golbeck, Jennifer}, doi = {10.1561/1800000006}, interhash = {4a024cc3eda1b4e359c2c8c7b2139244}, intrahash = {43c0e2991fa9a118d9757aa71184f9fd}, issn = {1555-077X}, journal = {Foundations and Trends in Web Science}, month = jan, number = 2, pages = {131--197}, publisher = {Now Publishers Inc.}, title = {Trust on the World Wide Web: A Survey}, url = {http://www.nowpublishers.com/product.aspx?doi=1800000006&product=WEB}, volume = 1, year = 2006 } @article{kosala00web, address = {New York, NY, USA}, author = {Kosala, R. and Blockeel, H.}, bibsource = {DBLP, http://dblp.uni-trier.de}, interhash = {99eea914954da48c9691277ce4e32932}, intrahash = {59f6ef686827c7095cc89ebdb056a222}, journal = {SIGKDD Explorations}, number = 1, pages = {1--15}, publisher = {ACM}, title = {Web Mining Research: {A} Survey}, url = {http://citeseer.nj.nec.com/kosala00web.html}, volume = 2, year = 2000 } @proceedings{Staab2004HOO, address = {Berlin; New York}, booktitle = {International handbooks on information systems}, editor = {Staab, Steffen and Studer, Rudi}, interhash = {494a7427b9dd11496d824c824b35938b}, intrahash = {f920f0aabbe7a02c9fe5d65c298bc8ea}, issn = {3540408347 9783540408345}, pages = {--}, publisher = {Springer}, refid = {53814725}, title = {Handbook on ontologies}, year = 2004 } @inproceedings{conf/dawak/MadriaBNL99, author = {Madria, Sanjay Kumar and Bhowmick, Sourav S. and Ng, Wee Keong and Lim, Ee-Peng}, booktitle = {DaWaK}, crossref = {conf/dawak/1999}, date = {2002-03-05}, editor = {Mohania, Mukesh K. and Tjoa, A. Min}, ee = {http://link.springer.de/link/service/series/0558/bibs/1676/16760303.htm}, interhash = {706390429ca5bf6e33d2fda37f956922}, intrahash = {1016d42a26ca0748ba227d62b7126933}, isbn = {3-540-66458-0}, pages = {303-312}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Research Issues in Web Data Mining.}, url = {http://dblp.uni-trier.de/db/conf/dawak/dawak99.html#MadriaBNL99}, volume = 1676, year = 1999 } @article{kb00web, author = {Kosala, R. and Blockeel, H.}, interhash = {99eea914954da48c9691277ce4e32932}, intrahash = {59f6ef686827c7095cc89ebdb056a222}, journal = {SIGKDD Explorations}, number = 1, pages = {1-15}, publisher = {ACM}, title = {Web Mining Research: {A} Survey}, url = {citeseer.nj.nec.com/kosala00web.html}, volume = 2, year = 2000 }