@inproceedings{mohammad2009using, abstract = {The number of research publications in various disciplines is growing exponentially. Researchers and scientists are increasingly finding themselves in the position of having to quickly understand large amounts of technical material. In this paper we present the first steps in producing an automatically generated, readily consumable, technical survey. Specifically we explore the combination of citation information and summarization techniques. Even though prior work (Teufel et al., 2006) argues that citation text is unsuitable for summarization, we show that in the framework of multi-document survey creation, citation texts can play a crucial role.}, acmid = {1620839}, address = {Stroudsburg, PA, USA}, author = {Mohammad, Saif and Dorr, Bonnie and Egan, Melissa and Hassan, Ahmed and Muthukrishan, Pradeep and Qazvinian, Vahed and Radev, Dragomir and Zajic, David}, booktitle = {Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics}, interhash = {7921a9a20f6780be90327aa4e104214e}, intrahash = {b6cd30a439667d97f12241836738203c}, isbn = {978-1-932432-41-1}, location = {Boulder, Colorado}, numpages = {9}, pages = {584--592}, publisher = {Association for Computational Linguistics}, series = {NAACL '09}, title = {Using citations to generate surveys of scientific paradigms}, url = {http://dl.acm.org/citation.cfm?id=1620754.1620839}, year = 2009 } @article{montaner2003taxonomy, abstract = {Recently, Artificial Intelligence techniques have proved useful inhelping users to handle the large amount of information on the Internet.The idea of personalized search engines, intelligent software agents,and recommender systems has been widely accepted among users who requireassistance in searching, sorting, classifying, filtering and sharingthis vast quantity of information. In this paper, we present astate-of-the-art taxonomy of intelligent recommender agents on theInternet. We have analyzed 37 different systems and their references andhave sorted them into a list of 8 basic dimensions. These dimensions arethen used to establish a taxonomy under which the systems analyzed areclassified. Finally, we conclude this paper with a cross-dimensionalanalysis with the aim of providing a starting point for researchers toconstruct their own recommender system.}, author = {Montaner, Miquel and López, Beatriz and de la Rosa, Josep Lluís}, doi = {10.1023/A:1022850703159}, interhash = {3753781e80f4118f1dd77d7637be2f8b}, intrahash = {f713e3f6acc112d9fbfd10216589d7db}, issn = {0269-2821}, journal = {Artificial Intelligence Review}, language = {English}, number = 4, pages = {285--330}, publisher = {Kluwer Academic Publishers}, title = {A Taxonomy of Recommender Agents on the Internet}, url = {http://dx.doi.org/10.1023/A%3A1022850703159}, volume = 19, year = 2003 } @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{balke2012introduction, abstract = {Transforming unstructured or semi-structured information into structured knowledge is one of the big challenges of today’s knowledge society. While this abstract goal is still unreached and probably unreachable, intelligent information extraction techniques are considered key ingredients on the way to generating and representing knowledge for a wide variety of applications. This is especially true for the current efforts to turn the World Wide Web being the world’s largest collection of information into the world’s largest knowledge base. This introduction gives a broad overview about the major topics and current trends in information extraction.}, address = {Berlin/Heidelberg}, affiliation = {Institut für Informationssysteme, Technische Universität Braunschweig, Braunschweig, Germany}, author = {Balke, Wolf-Tilo}, doi = {10.1007/s13222-012-0090-x}, interhash = {0127ba6c59c3f7f7121429eb098a4b90}, intrahash = {992b3c989c8fda7c58cd9262e2f70907}, issn = {1618-2162}, journal = {Datenbank-Spektrum}, keyword = {Computer Science}, number = 2, pages = {81--88}, publisher = {Springer}, title = {Introduction to Information Extraction: Basic Notions and Current Trends}, url = {http://dx.doi.org/10.1007/s13222-012-0090-x}, volume = 12, year = 2012 } @inproceedings{yuen2009survey, abstract = {Human computation is a technique that makes use of human abilities for computation to solve problems. The human computation problems are the problems those computers are not good at solving but are trivial for humans. In this paper, we give a survey of various human computation systems which are categorized into initiatory human computation, distributed human computation and social game-based human computation with volunteers, paid engineers and online players. For the existing large number of social games, some previous works defined various types of social games, but the recent developed social games cannot be categorized based on the previous works. In this paper, we define the categories and the characteristics of social games which are suitable for all existing ones. Besides, we present a survey on the performance aspects of human computation system. This paper gives a better understanding on human computation system.}, author = {Yuen, Man-Ching and Chen, Ling-Jyh and King, I.}, booktitle = {Proceedings of the International Conference on Computational Science and Engineering, CSE '09}, doi = {10.1109/CSE.2009.395}, interhash = {69f9bd3e6a721f226e39e1f990e20286}, intrahash = {8670a20dbf6aa9dd21da81ab78a1e333}, month = aug, pages = {723--728}, title = {A Survey of Human Computation Systems}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5283450&tag=1}, volume = 4, year = 2009 } @inproceedings{quinn2011human, abstract = {The rapid growth of human computation within research and industry has produced many novel ideas aimed at organizing web users to do great things. However, the growth is not adequately supported by a framework with which to understand each new system in the context of the old. We classify human computation systems to help identify parallels between different systems and reveal "holes" in the existing work as opportunities for new research. Since human computation is often confused with "crowdsourcing" and other terms, we explore the position of human computation with respect to these related topics.}, acmid = {1979148}, address = {New York, NY, USA}, author = {Quinn, Alexander J. and Bederson, Benjamin B.}, booktitle = {Proceedings of the 2011 annual conference on Human factors in computing systems}, doi = {10.1145/1978942.1979148}, interhash = {f319e8c67a7af1afd804774ccba7b717}, intrahash = {3524eeb1e7a62c5bfbe0cec74a14af21}, isbn = {978-1-4503-0228-9}, location = {Vancouver, BC, Canada}, numpages = {10}, pages = {1403--1412}, publisher = {ACM}, title = {Human computation: a survey and taxonomy of a growing field}, url = {http://doi.acm.org/10.1145/1978942.1979148}, year = 2011 } @incollection{poelmans2010formal, abstract = {In this paper, we analyze the literature on Formal Concept Analysis (FCA) using FCA. We collected 702 papers published between 2003-2009 mentioning Formal Concept Analysis in the abstract. We developed a knowledge browsing environment to support our literature analysis process. The pdf-files containing the papers were converted to plain text and indexed by Lucene using a thesaurus containing terms related to FCA research. We use the visualization capabilities of FCA to explore the literature, to discover and conceptually represent the main research topics in the FCA community. As a case study, we zoom in on the 140 papers on using FCA in knowledge discovery and data mining and give an extensive overview of the contents of this literature.}, address = {Berlin/Heidelberg}, author = {Poelmans, Jonas and Elzinga, Paul and Viaene, Stijn and Dedene, Guido}, booktitle = {Conceptual Structures: From Information to Intelligence}, doi = {10.1007/978-3-642-14197-3_15}, editor = {Croitoru, Madalina and Ferré, Sébastien and Lukose, Dickson}, interhash = {713d63f847ff4b2cbf613fc0508eb31b}, intrahash = {9694689a034cc02aae1e27114ca26a94}, isbn = {978-3-642-14196-6}, pages = {139--153}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Formal Concept Analysis in Knowledge Discovery: A Survey}, url = {http://dx.doi.org/10.1007/978-3-642-14197-3_15}, volume = 6208, year = 2010 } @article{zhang2011tagaware, abstract = {In the past decade, Social Tagging Systems have attracted increasing attention from both physical and computer science communities. Besides the underlying structure and dynamics of tagging systems, many efforts have been addressed to unify tagging information to reveal user behaviors and preferences, extract the latent semantic relations among items, make recommendations, and so on. Specifically, this article summarizes recent progress about tag-aware recommender systems, emphasizing on the contributions from three mainstream perspectives and approaches: network-based methods, tensor-based methods, and the topic-based methods. Finally, we outline some other tag-related studies and future challenges of tag-aware recommendation algorithms.}, affiliation = {Institute of Information Economy, Hangzhou Normal University, Hangzhou, 310036 China}, author = {Zhang, Zi-Ke and Zhou, Tao and Zhang, Yi-Cheng}, doi = {10.1007/s11390-011-0176-1}, interhash = {c1f382191eab1f80aaf8cf425c376600}, intrahash = {67b105a941f0a557c6d457447625cbfb}, issn = {1000-9000}, issue = {5}, journal = {Journal of Computer Science and Technology}, keyword = {Computer Science}, number = 5, pages = {767--777}, publisher = {Springer Boston}, title = {Tag-Aware Recommender Systems: A State-of-the-Art Survey}, url = {http://dx.doi.org/10.1007/s11390-011-0176-1}, volume = 26, year = 2011 } @article{milicevic2010social, abstract = {Social tagging systems have grown in popularity over the Web in the last years on account of their simplicity to categorize and retrieve content using open-ended tags. The increasing number of users providing information about themselves through social tagging activities caused the emergence of tag-based profiling approaches, which assume that users expose their preferences for certain contents through tag assignments. Thus, the tagging information can be used to make recommendations. This paper presents an overview of the field of social tagging systems which can be used for extending the capabilities of recommender systems. Various limitations of the current generation of social tagging systems and possible extensions that can provide better recommendation capabilities are also considered.}, author = {Milicevic, Aleksandra and Nanopoulos, Alexandros and Ivanovic, Mirjana}, doi = {10.1007/s10462-009-9153-2}, interhash = {d9e331d46fe4da88400036ad404c4535}, intrahash = {efb6cb6220dfdd1e3d9ca4894e9f1459}, issn = {0269-2821}, journal = {Artificial Intelligence Review}, month = jan, number = 3, pages = {187--209}, publisher = {Springer Netherlands}, title = {Social tagging in recommender systems: a survey of the state-of-the-art and possible extensions}, url = {http://dx.doi.org/10.1007/s10462-009-9153-2}, volume = 33, year = 2010 } @inproceedings{dattolo2010recommendation, abstract = {Social tagging is an innovative and powerful mechanism introduced with Web 2.0: it shifts the task of classifying resources from a reduced set of knowledge engineers to the wide set of Web users. Users of social tagging systems define personal classifications which can be used by other peers for browsing available resources. However, due to the absence of rules for managing the tagging process, and to the lack of predefined schemas or structures for inserting metadata and relationships among tags, current user generated classifications dop not produce sound taxonomies. This is a strong limitation which prevents an effective and informed resource sharing. For this reason researchers are modeling innovative recommender systems capable to better support tagging, browsing, and searching for new resources. This paper is a survey which discusses the role of tags in recommender systems: starting from social tagging systems, we analyze various techniques for suggesting content and we introduce the approaches exploited for proposing tags for classifying resources, considering both personalized and not-personalized recommendation.}, author = {Dattolo, A. and Ferrara, F. and Tasso, C.}, booktitle = {Proc. of the 3rd International Conference on Human System Interaction - HSI'2010}, doi = {10.1109/HSI.2010.5514515}, interhash = {447e607c362f0e948f1da10a0af6e111}, intrahash = {aea6ea6f248a233c9609a93a2e1ee7fa}, month = may, pages = {548--555}, publisher = {IEEE Press}, title = {The role of tags for recommendation: a survey.}, url = {http://sole.dimi.uniud.it/~antonina.dattolo/papers/2010/conference/dattolo-hsi2010.pdf}, year = 2010 } @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{battista1994algorithms, abstract = {Several data presentation problems involve drawing graphs so that they are easy to read and understand. Examples include circuit schematics and software engineering diagrams. In this paper we present a bibliographic survey on algorithms whose goal is to produce aesthetically pleasing drawings of graphs. Research on this topic is spread over the broad spectrum of Computer Science. This bibliography constitutes an attempt to encompass both theoretical and application oriented papers from disparate areas.}, address = {Amsterdam, The Netherlands}, author = {Battista, Giuseppe Di and Eades, Peter and Tamassia, Roberto and Tollis, Ioannis G.}, doi = {10.1016/0925-7721(94)00014-X}, interhash = {c8010ae4e2e0aedf21607631ac79bed4}, intrahash = {a62ded9eee008659ffa33d294b8de870}, issn = {0925-7721}, journal = {Computational Geometry: Theory and Applications}, number = 5, pages = {235--282}, publisher = {Elsevier Science Publishers B. V.}, title = {Algorithms for drawing graphs: an annotated bibliography}, url = {http://portal.acm.org/citation.cfm?id=195598}, volume = 4, year = 1994 } @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{burke2002hybrid, abstract = {Recommender systems represent user preferences for the purpose of suggesting items to purchase or examine. They have become fundamental applications in electronic commerce and information access, providing suggestions that effectively prune large information spaces so that users are directed toward those items that best meet their needs and preferences. A variety of techniques have been proposed for performing recommendation, including content-based, collaborative, knowledge-based and other techniques. To improve performance, these methods have sometimes been combined in hybrid recommenders. This paper surveys the landscape of actual and possible hybrid recommenders, and introduces a novel hybrid, EntreeC, a system that combines knowledge-based recommendation and collaborative filtering to recommend restaurants. Further, we show that semantic ratings obtained from the knowledge-based part of the system enhance the effectiveness of collaborative filtering.}, address = {Hingham, MA, USA}, author = {Burke, Robin}, doi = {10.1023/A:1021240730564}, interhash = {f40020400b8bc08adca29a987caf25d8}, intrahash = {460b623792e13b4ec0e990563e57f26c}, issn = {0924-1868}, journal = {User Modeling and User-Adapted Interaction}, month = nov, number = 4, pages = {331--370}, publisher = {Kluwer Academic Publishers}, title = {Hybrid Recommender Systems: Survey and Experiments}, url = {http://portal.acm.org/citation.cfm?id=586352}, volume = 12, year = 2002 } @article{romero07, abstract = {Currently there is an increasing interest in data mining and educational systems, making educational data mining as a new growing research community. This paper surveys the application of data mining to traditional educational systems, particular web-based courses, well-known learning content management systems, and adaptive and intelligent web-based educational systems. Each of these systems has different data source and objectives for knowledge discovering. After preprocessing the available data in each case, data mining techniques can be applied: statistics and visualization; clustering, classification and outlier detection; association rule mining and pattern mining; and text mining. The success of the plentiful work needs much more specialized work in order for educational data mining to become a mature area.}, address = {Tarrytown, NY, USA}, author = {Romero, C. and Ventura, S.}, doi = {http://dx.doi.org/10.1016/j.eswa.2006.04.005}, interhash = {89d843f1a3b181f2a628e881d9210b22}, intrahash = {746d12e92e58587461ffcb8dc381e283}, issn = {0957-4174}, journal = {Expert Syst. Appl.}, number = 1, pages = {135--146}, publisher = {Pergamon Press, Inc.}, title = {Educational data mining: A survey from 1995 to 2005}, url = {http://portal.acm.org/citation.cfm?id=1223659}, volume = 33, year = 2007 } @article{954342, abstract = {As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide range of commercial and law enforcement applications, and the second is the availability of feasible technologies after 30 years of research. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the conditions imposed by many real applications. For example, recognition of face images acquired in an outdoor environment with changes in illumination and/or pose remains a largely unsolved problem. In other words, current systems are still far away from the capability of the human perception system.This paper provides an up-to-date critical survey of still- and video-based face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition, relevant topics such as psychophysical studies, system evaluation, and issues of illumination and pose variation are covered.}, address = {New York, NY, USA}, author = {Zhao, W. and Chellappa, R. and Phillips, P. J. and Rosenfeld, A.}, interhash = {0a8e3859cc7f6ea7bd51af1ee9ca1b36}, intrahash = {549485a2446eef075c15c9a4ad00c64a}, issn = {0360-0300}, journal = {ACM Comput. Surv.}, number = 4, pages = {399--458}, publisher = {ACM Press}, title = {Face recognition: A literature survey}, url = {http://doi.acm.org/10.1145/954339.954342}, volume = 35, year = 2003 } @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 }