@inproceedings{doerfel2012publication, abstract = {We present an analysis of the publication and citation networks of all previous editions of the three conferences most relevant to the FCA community: ICFCA, ICCS and CLA. Using data mining methods from FCA and graph analysis, we investigate patterns and communities among authors, we identify and visualize influential publications and authors, and we give a statistical summary of the conferences’ history. }, address = {Berlin/Heidelberg}, author = {Doerfel, Stephan and Jäschke, Robert and Stumme, Gerd}, booktitle = {Formal Concept Analysis}, doi = {10.1007/978-3-642-29892-9_12}, editor = {Domenach, F. and Ignatov, D.I. and Poelmans, J.}, interhash = {f34f31e8dd1e07b1b0a5ab688f10084a}, intrahash = {9207cd4b1cf7d87c9ae959ac780e152c}, isbn = {978-3-642-29891-2}, month = may, pages = {77--95}, publisher = {Springer}, series = {Lecture Notes in Artificial Intelligence}, title = {Publication Analysis of the Formal Concept Analysis Community}, url = {http://link.springer.com/chapter/10.1007/978-3-642-29892-9_12}, volume = 7278, year = 2012 } @inproceedings{Strohman:2007:RCA:1277741.1277868, abstract = {We approach the problem of academic literature search by considering an unpublished manuscript as a query to a search system. We use the text of previous literature as well as the citation graph that connects it to find relevant related material. We evaluate our technique with manual and automatic evaluation methods, and find an order of magnitude improvement in mean average precision as compared to a text similarity baseline.}, acmid = {1277868}, address = {New York, NY, USA}, author = {Strohman, Trevor and Croft, W. Bruce and Jensen, David}, booktitle = {Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval}, doi = {10.1145/1277741.1277868}, interhash = {a34279add7d7a9f3c564735b7b8dcd44}, intrahash = {7a0b1ff2a40b3989ef8d83daabd91159}, isbn = {978-1-59593-597-7}, location = {Amsterdam, The Netherlands}, numpages = {2}, pages = {705--706}, publisher = {ACM}, title = {Recommending citations for academic papers}, url = {http://doi.acm.org/10.1145/1277741.1277868}, year = 2007 } @inproceedings{he2010contextaware, abstract = {When you write papers, how many times do you want to make some citations at a place but you are not sure which papers to cite? Do you wish to have a recommendation system which can recommend a small number of good candidates for every place that you want to make some citations? In this paper, we present our initiative of building a context-aware citation recommendation system. High quality citation recommendation is challenging: not only should the citations recommended be relevant to the paper under composition, but also should match the local contexts of the places citations are made. Moreover, it is far from trivial to model how the topic of the whole paper and the contexts of the citation places should affect the selection and ranking of citations. To tackle the problem, we develop a context-aware approach. The core idea is to design a novel non-parametric probabilistic model which can measure the context-based relevance between a citation context and a document. Our approach can recommend citations for a context effectively. Moreover, it can recommend a set of citations for a paper with high quality. We implement a prototype system in CiteSeerX. An extensive empirical evaluation in the CiteSeerX digital library against many baselines demonstrates the effectiveness and the scalability of our approach.}, acmid = {1772734}, address = {New York, NY, USA}, author = {He, Qi and Pei, Jian and Kifer, Daniel and Mitra, Prasenjit and Giles, Lee}, booktitle = {Proceedings of the 19th international conference on World wide web}, doi = {10.1145/1772690.1772734}, interhash = {d48586d4ee897859c5d797e671f3e384}, intrahash = {17f7aa5c8bf1d9055fd83688f46fde65}, isbn = {978-1-60558-799-8}, location = {Raleigh, North Carolina, USA}, numpages = {10}, pages = {421--430}, publisher = {ACM}, title = {Context-aware citation recommendation}, url = {http://doi.acm.org/10.1145/1772690.1772734}, year = 2010 } @incollection{springerlink:10.1007/978-3-642-01307-2_55, address = {Berlin/Heidelberg}, affiliation = {Department of Computer Science and Technology, Tsinghua University, Beijing, 100084 China}, author = {Tang, Jie and Zhang, Jing}, booktitle = {Advances in Knowledge Discovery and Data Mining}, doi = {10.1007/978-3-642-01307-2_55}, editor = {Theeramunkong, Thanaruk and Kijsirikul, Boonserm and Cercone, Nick and Ho, Tu-Bao}, interhash = {c429474403bcd28561f8ab4fa436d036}, intrahash = {983b4eaae55e0d5e5c628a13bf58324c}, isbn = {978-3-642-01306-5}, keyword = {Computer Science}, pages = {572--579}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {A Discriminative Approach to Topic-Based Citation Recommendation}, url = {http://dx.doi.org/10.1007/978-3-642-01307-2_55}, volume = 5476, year = 2009 } @inproceedings{bethard2010should, abstract = {Scientists depend on literature search to find prior work that is relevant to their research ideas. We introduce a retrieval model for literature search that incorporates a wide variety of factors important to researchers, and learns the weights of each of these factors by observing citation patterns. We introduce features like topical similarity and author behavioral patterns, and combine these with features from related work like citation count and recency of publication. We present an iterative process for learning weights for these features that alternates between retrieving articles with the current retrieval model, and updating model weights by training a supervised classifier on these articles. We propose a new task for evaluating the resulting retrieval models, where the retrieval system takes only an abstract as its input and must produce as output the list of references at the end of the abstract's article. We evaluate our model on a collection of journal, conference and workshop articles from the ACL Anthology Reference Corpus. Our model achieves a mean average precision of 28.7, a 12.8 point improvement over a term similarity baseline, and a significant improvement both over models using only features from related work and over models without our iterative learning.}, acmid = {1871517}, address = {New York, NY, USA}, author = {Bethard, Steven and Jurafsky, Dan}, booktitle = {Proceedings of the 19th ACM international conference on Information and knowledge management}, doi = {10.1145/1871437.1871517}, interhash = {1cdf6c7da38af251279e9fb915266af2}, intrahash = {369206c7472baeaa5ecefef586e16c6a}, isbn = {978-1-4503-0099-5}, location = {Toronto, ON, Canada}, numpages = {10}, pages = {609--618}, publisher = {ACM}, title = {Who should I cite: learning literature search models from citation behavior}, url = {http://doi.acm.org/10.1145/1871437.1871517}, year = 2010 } @inproceedings{he2011citation, abstract = {Automatic recommendation of citations for a manuscript is highly valuable for scholarly activities since it can substantially improve the efficiency and quality of literature search. The prior techniques placed a considerable burden on users, who were required to provide a representative bibliography or to mark passages where citations are needed. In this paper we present a system that considerably reduces this burden: a user simply inputs a query manuscript (without a bibliography) and our system automatically finds locations where citations are needed. We show that naïve approaches do not work well due to massive noise in the document corpus. We produce a successful approach by carefully examining the relevance between segments in a query manuscript and the representative segments extracted from a document corpus. An extensive empirical evaluation using the CiteSeerX data set shows that our approach is effective.}, acmid = {1935926}, address = {New York, NY, USA}, author = {He, Qi and Kifer, Daniel and Pei, Jian and Mitra, Prasenjit and Giles, C. Lee}, booktitle = {Proceedings of the fourth ACM international conference on Web search and data mining}, doi = {10.1145/1935826.1935926}, interhash = {7e98aaf26a7ed6cc624249a3ab570d7a}, intrahash = {bbd320f03d13c6cfff4b6f9e6b4630f7}, isbn = {978-1-4503-0493-1}, location = {Hong Kong, China}, numpages = {10}, pages = {755--764}, publisher = {ACM}, title = {Citation recommendation without author supervision}, url = {http://doi.acm.org/10.1145/1935826.1935926}, year = 2011 } @inproceedings{wang2010claper, abstract = {Classical papers are of great help for beginners to get familiar with a new research area. However, digging them out is a difficult problem. This paper proposes Claper, a novel academic recommendation system based on two proven principles: the Principle of Download Persistence and the Principle of Citation Approaching (we prove them based on real-world datasets). The principle of download persistence indicates that classical papers have few decreasing download frequencies since they were published. The principle of citation approaching indicates that a paper which cites a classical paper is likely to cite citations of that classical paper. Our experimental results based on large-scale real-world datasets illustrate Claper can effectively recommend classical papers of high quality to beginners and thus help them enter their research areas.}, author = {Wang, Yonggang and Zhai, Ennan and Hu, Jianbin and Chen, Zhong}, booktitle = {Proceedings of the seventh International Conference on Fuzzy Systems and Knowledge Discovery}, doi = {10.1109/FSKD.2010.5569227}, interhash = {7180ddaf1c1765a45fd244027bd0bf43}, intrahash = {7da72bf2f0538afad9377a0d50c263b4}, month = aug, pages = {2777--2781}, publisher = {IEEE}, title = {Claper: Recommend classical papers to beginners}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5569227}, volume = 6, year = 2010 } @article{evans2010friends, abstract = {Prior research in the social search space has focused on the informational benefits of collaborating with others during web and workplace information seeking. However, social interactions, especially during complex tasks, can have cognitive benefits as well. Our goal in this paper is to document the methods and outcomes of using social resources to help with exploratory search tasks. We used a talk-aloud protocol and video capture to explore the actions of eight subjects as they completed two ''Google-hard'' search tasks. Task questions were alternated between a Social and Non-Social Condition. The Social Condition restricted participants to use only social resources-search engines were not allowed. The Non-Social Condition permitted normal web-based information sources, but restricted the use of social tools. We describe the social tactics our participants used in their search process. Asking questions on social networking sites and targeting friends one-on-one both resulted in increased information processing but during different phases of the question-answering process. Participants received more responses via social networking sites but more thorough answers in private channels (one-on-one). We discuss the possibility that the technological and cultural affordances of different social-informational media may provide complementary cognitive benefits to searchers. Our work suggests that online social tools could be better integrated with each other and with existing search facilities. We conclude with a discussion of our findings and implications for the design of social search tools. }, address = {Tarrytown, NY, USA}, author = {Evans, Brynn M. and Kairam, Sanjay and Pirolli, Peter}, doi = {10.1016/j.ipm.2009.12.001}, interhash = {b6beecb1f1fb1500a3c9b7732190e4ff}, intrahash = {835394af0d9f7776978ec7f3e10cae13}, issn = {0306-4573}, journal = {Information Processing & Management}, month = nov, number = 6, numpages = {14}, pages = {679--692}, publisher = {Pergamon Press, Inc.}, title = {Do your friends make you smarter?: An analysis of social strategies in online information seeking}, url = {http://dx.doi.org/10.1016/j.ipm.2009.12.001}, volume = 46, year = 2010 } @inproceedings{pavlovic2012quantitative, abstract = {Formal Concept Analysis (FCA) begins from a context, given as a binary relation between some objects and some attributes, and derives a lattice of concepts, where each concept is given as a set of objects and a set of attributes, such that the first set consists of all objects that satisfy all attributes in the second, and vice versa. Many applications, though, provide contexts with quantitative information, telling not just whether an object satisfies an attribute, but also quantifying this satisfaction. Contexts in this form arise as rating matrices in recommender systems, as occurrence matrices in text analysis, as pixel intensity matrices in digital image processing, etc. Such applications have attracted a lot of attention, and several numeric extensions of FCA have been proposed. We propose the framework of proximity sets (proxets), which subsume partially ordered sets (posets) as well as metric spaces. One feature of this approach is that it extracts from quantified contexts quantified concepts, and thus allows full use of the available information. Another feature is that the categorical approach allows analyzing any universal properties that the classical FCA and the new versions may have, and thus provides structural guidance for aligning and combining the approaches.}, address = {Berlin/Heidelberg}, author = {Pavlovic, Dusko}, booktitle = {ICFCA 2012}, editor = {Domenach, F. and Ignatov, D.I. and Poelmans, J.}, ee = {http://arxiv.org/abs/1204.5802}, interhash = {601aaf1dbcb15e8872109be6f4a1a5d8}, intrahash = {a0c8122fe1a490e82129a24e042b371d}, issn = {0302-9743}, pages = {260--277}, publisher = {Springer}, series = {Lecture Notes in Artificial Intelligence}, title = {Quantitative Concept Analysis}, volume = 7278, year = 2012 } @article{pham2011development, abstract = {In contrast to many other scientific disciplines, computer science considers conference publications. Conferences have the advantage of providing fast publication of papers and of bringing researchers together to present and discuss the paper with peers. Previous work on knowledge mapping focused on the map of all sciences or a particular domain based on ISI published Journal Citation Report (JCR). Although this data cover most of the important journals, it lacks computer science conference and workshop proceedings, which results in an imprecise and incomplete analysis of the computer science knowledge. This paper presents an analysis on the computer science knowledge network constructed from all types of publications, aiming at providing a complete view of computer science research. Based on the combination of two important digital libraries (DBLP and CiteSeerX), we study the knowledge network created at journal/conference level using citation linkage, to identify the development of sub-disciplines. We investigate the collaborative and citation behavior of journals/conferences by analyzing the properties of their co-authorship and citation subgraphs. The paper draws several important conclusions. First, conferences constitute social structures that shape the computer science knowledge. Second, computer science is becoming more interdisciplinary. Third, experts are the key success factor for sustainability of journals/conferences.}, address = {Wien}, affiliation = {Information Systems and Database Technology, RWTH Aachen University, Aachen, Ahornstr. 55, 52056 Aachen, Germany}, author = {Pham, Manh and Klamma, Ralf and Jarke, Matthias}, doi = {10.1007/s13278-011-0024-x}, interhash = {193312234ed176aa8be9f35d4d1c4e72}, intrahash = {8ae08cacda75da80bfa5604cfce48449}, issn = {1869-5450}, journal = {Social Network Analysis and Mining}, keyword = {Computer Science}, number = 4, pages = {321--340}, publisher = {Springer}, title = {Development of computer science disciplines: a social network analysis approach}, url = {http://dx.doi.org/10.1007/s13278-011-0024-x}, volume = 1, year = 2011 } @inproceedings{brew2010using, abstract = {Tracking sentiment in the popular media has long been of interest to media analysts and pundits. With the availability of news content via online syndicated feeds, it is now possible to automate some aspects of this process. There is also great potential to crowdsource Crowdsourcing is a term, sometimes associated with Web 2.0 technologies, that describes outsourcing of tasks to a large often anonymous community. much of the annotation work that is required to train a machine learning system to perform sentiment scoring. We describe such a system for tracking economic sentiment in online media that has been deployed since August 2009. It uses annotations provided by a cohort of non-expert annotators to train a learning system to classify a large body of news items. We report on the design challenges addressed in managing the effort of the annotators and in making annotation an interesting experience.}, acmid = {1860997}, address = {Amsterdam, The Netherlands, The Netherlands}, author = {Brew, Anthony and Greene, Derek and Cunningham, Pádraig}, booktitle = {Proceedings of the 19th European Conference on Artificial Intelligence}, editor = {Coelho, Helder and Studer, Rudi and Wooldridge, Michael}, interhash = {90650749ea1084b729710d37b5865b72}, intrahash = {9643e3c5729886b0b4e85cb3d3d704f5}, isbn = {978-1-60750-605-8}, numpages = {6}, pages = {145--150}, publisher = {IOS Press}, series = {Frontiers in Artificial Intelligence and Applications}, title = {Using Crowdsourcing and Active Learning to Track Sentiment in Online Media}, url = {http://dl.acm.org/citation.cfm?id=1860967.1860997}, volume = 215, year = 2010 } @article{stirling2012archives, abstract = {The Internet has been covered by legal deposit legislation in France since 2006, making web archiving one of the missions of the Bibliothèque nationale de France (BnF). Access to the web archives has been provided in the library on an experimental basis since 2008. In the context of increasing interest in many countries in web archiving and how it may best serve the needs of researchers, especially in the expanding field of Internet studies for social sciences, a qualitative study was performed, based on interviews with potential users of the web archives held at the BnF, and particularly researchers working in various areas related to the Internet. The study aimed to explore their needs in terms of both content and services, and also to analyse different ways of representing the archives, in order to identify ways of increasing their use. While the interest of maintaining the "memory" of the web is obvious to the researchers, they are faced with the difficulty of defining, in what is a seemingly limitless space, meaningful collections of documents. Cultural heritage institutions such as national libraries are perceived as trusted third parties capable of creating rationally-constructed and well-documented collections, but such archives raise certain ethical and methodological questions.}, author = {Stirling, Peter and Chevallier, Philippe and Illien, Gildas}, doi = {10.1045/march2012-stirling}, interhash = {a783191c99a285197525595ebf509bb2}, intrahash = {4f7840193e7e435ad5dd0003fc93691a}, issn = {1082-9873}, journal = {D-Lib Magazine}, month = {March/April }, number = {3/4}, title = {Web Archives for Researchers: Representations, Expectations and Potential Uses}, url = {http://www.dlib.org/dlib/march12/stirling/03stirling.html}, volume = 18, year = 2012 } @incollection{kitsuregawa2008sociosense, abstract = {We introduce Socio-Sense Web analysis system. The system applies structural and temporal analysis methods to long term Web archive to obtain insight into the real society. We present an overview of the system and core methods followed by excerpts from case studies on consumer behavior analyses.}, address = {Berlin/Heidelberg}, affiliation = {The University of Tokyo Institute of Industrial Science 4–6–1 Komaba Meguro-ku Tokyo 153-8505 Japan}, author = {Kitsuregawa, Masaru and Tamura, Takayuki and Toyoda, Masashi and Kaji, Nobuhiro}, booktitle = {Progress in WWW Research and Development}, doi = {10.1007/978-3-540-78849-2_1}, editor = {Zhang, Yanchun and Yu, Ge and Bertino, Elisa and Xu, Guandong}, interhash = {a0ac63893d45095766b0f5fc8fd78139}, intrahash = {76f35c47a4b65f229269ea9ea39829d8}, isbn = {978-3-540-78848-5}, keyword = {Computer Science}, pages = {1--8}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Socio-Sense: A System for Analysing the Societal Behavior from Long Term Web Archive}, url = {http://dx.doi.org/10.1007/978-3-540-78849-2_1}, volume = 4976, year = 2008 } @article{cho2006stanford, abstract = {We describe the design and performance of WebBase, a tool for Web research. The system includes a highly customizable crawler, a repository for collected Web pages, an indexer for both text and link-related page features, and a high-speed content distribution facility. The distribution module enables researchers world-wide to retrieve pages from WebBase, and stream them across the Internet at high speed. The advantage for the researchers is that they need not all crawl the Web before beginning their research. WebBase has been used by scores of research and teaching organizations world-wide, mostly for investigations into Web topology and linguistic content analysis. After describing the system's architecture, we explain our engineering decisions for each of the WebBase components, and present respective performance measurements.}, acmid = {1149124}, address = {New York, NY, USA}, author = {Cho, Junghoo and Garcia-Molina, Hector and Haveliwala, Taher and Lam, Wang and Paepcke, Andreas and Raghavan, Sriram and Wesley, Gary}, doi = {10.1145/1149121.1149124}, interhash = {bebbc072ea2dccf4c2b27abf244c1f08}, intrahash = {3cd21bf8a87619e0489b8da177c9f0b4}, issn = {1533-5399}, issue_date = {May 2006}, journal = {ACM Transactions on Internet Technology}, month = may, number = 2, numpages = {34}, pages = {153--186}, publisher = {ACM}, title = {Stanford WebBase components and applications}, url = {http://doi.acm.org/10.1145/1149121.1149124}, volume = 6, year = 2006 } @article{melnik2010dremel, abstract = {Dremel is a scalable, interactive ad-hoc query system for analysis of read-only nested data. By combining multi-level execution trees and columnar data layout, it is capable of running aggregation queries over trillion-row tables in seconds. The system scales to thousands of CPUs and petabytes of data, and has thousands of users at Google. In this paper, we describe the architecture and implementation of Dremel, and explain how it complements MapReduce-based computing. We present a novel columnar storage representation for nested records and discuss experiments on few-thousand node instances of the system.}, acmid = {1920886}, author = {Melnik, Sergey and Gubarev, Andrey and Long, Jing Jing and Romer, Geoffrey and Shivakumar, Shiva and Tolton, Matt and Vassilakis, Theo}, interhash = {43835c06736099c3ebc4aaa1c9d38dbb}, intrahash = {5dae1fdc088eb801ef7663d3b35120ed}, issn = {2150-8097}, issue_date = {September 2010}, journal = {Proceedings of the VLDB Endowment}, month = sep, number = {1-2}, numpages = {10}, pages = {330--339}, publisher = {VLDB Endowment}, title = {Dremel: interactive analysis of web-scale datasets}, url = {http://dl.acm.org/citation.cfm?id=1920841.1920886}, volume = 3, year = 2010 } @inproceedings{weikum2011longitudinal, abstract = {Organizations like the Internet Archive have been capturing Web contents over decades, building up huge repositories of time-versioned pages. The timestamp annotations and the sheer volume of multi-modal content constitutes a gold mine for analysts of all sorts, across diff�erent application areas, from political analysts and marketing agencies to academic researchers and product developers. In contrast to traditional data analytics on click logs, the focus is on longitudinal studies over very long horizons. This longitudinal aspect affects and concerns all data and metadata, from the content itself, to the indices and the statistical metadata maintained for it. Moreover, advanced analysts prefer to deal with semantically rich entities like people, places, organizations, and ideally relationships such as company acquisitions, instead of, say, Web pages containing such references. For example, tracking and analyzing a politician's public appearances over a decade is much harder than mining frequently used query words or frequently clicked URLs for the last month. The huge size of Web archives adds to the complexity of this daunting task. This paper discusses key challenges, that we intend to take up, which are posed by this kind of longitudinal analytics: time-travel indexing and querying, entity detection and tracking along the time axis, algorithms for advanced analyses and knowledge discovery, and scalability and platform issues.}, author = {Weikum, Gerhard and Ntarmos, Nikos and Spaniol, Marc and Triantafillou, Peter and Benczúr, András and Kirkpatrick, Scott and Rigaux, Philippe and Williamson, Mark}, booktitle = {Proceedings of the 5th Biennial Conference on Innovative Data Systems Research}, interhash = {2d84fdbf82a84bfc557056df3d0dcf11}, intrahash = {6ffcc0d793bbe53bf6ed17f9d929846e}, month = jan, pages = {199--202}, title = {Longitudinal Analytics on Web Archive Data: It's About Time!}, url = {http://www.cidrdb.org/cidr2011/Papers/CIDR11_Paper26.pdf}, year = 2011 } @article{alsubaiee2012asterix, abstract = {At UC Irvine, we are building a next generation parallel database system, called ASTERIX, as our approach to addressing today's "Big Data" management challenges. ASTERIX aims to combine time-tested principles from parallel database systems with those of the Web-scale computing community, such as fault tolerance for long running jobs. In this demo, we present a whirlwind tour of ASTERIX, highlighting a few of its key features. We will demonstrate examples of our data definition language to model semi-structured data, and examples of interesting queries using our declarative query language. In particular, we will show the capabilities of ASTERIX for answering geo-spatial queries and fuzzy queries, as well as ASTERIX' data feed construct for continuously ingesting data.}, acmid = {2367532}, author = {Alsubaiee, Sattam and Altowim, Yasser and Altwaijry, Hotham and Behm, Alexander and Borkar, Vinayak and Bu, Yingyi and Carey, Michael and Grover, Raman and Heilbron, Zachary and Kim, Young-Seok and Li, Chen and Onose, Nicola and Pirzadeh, Pouria and Vernica, Rares and Wen, Jian}, interhash = {ae521b66302adb1b7df3f4cdb8d92181}, intrahash = {003f2654ae41861cfb77bf0353634ac3}, issn = {2150-8097}, issue_date = {August 2012}, journal = {Proceedings of the VLDB Endowment}, month = aug, number = 12, numpages = {4}, pages = {1898--1901}, publisher = {VLDB Endowment}, title = {ASTERIX: an open source system for "Big Data" management and analysis (demo)}, url = {http://dl.acm.org/citation.cfm?id=2367502.2367532}, volume = 5, year = 2012 } @article{dainotti2012extracting, abstract = {Unsolicited one-way Internet traffic, also called Internet background radiation (IBR), has been used for years to study malicious activity on the Internet, including worms, DoS attacks, and scanning address space looking for vulnerabilities to exploit. We show how such traffic can also be used to analyze macroscopic Internet events that are unrelated to malware. We examine two phenomena: country-level censorship of Internet communications described in recent work, and natural disasters (two recent earthquakes). We introduce a new metric of local IBR activity based on the number of unique IP addresses per hour contributing to IBR. The advantage of this metric is that it is not affected by bursts of traffic from a few hosts. Although we have only scratched the surface, we are convinced that IBR traffic is an important building block for comprehensive monitoring, analysis, and possibly even detection of events unrelated to the IBR itself. In particular, IBR offers the opportunity to monitor the impact of events such as natural disasters on network infrastructure, and in particular reveals a view of events that is complementary to many existing measurement platforms based on (BGP) control-plane views or targeted active ICMP probing.}, acmid = {2096154}, address = {New York, NY, USA}, author = {Dainotti, Alberto and Amman, Roman and Aben, Emile and Claffy, Kimberly C.}, doi = {10.1145/2096149.2096154}, interhash = {7c97d11971a9b652c00e0487bfc79d54}, intrahash = {dc796731675fad942af97e1bd0c17366}, issn = {0146-4833}, journal = {SIGCOMM Computer Communication Review}, month = jan, number = 1, numpages = {9}, pages = {31--39}, publisher = {ACM}, title = {Extracting benefit from harm: using malware pollution to analyze the impact of political and geophysical events on the internet}, url = {http://doi.acm.org/10.1145/2096149.2096154}, volume = 42, year = 2012 } @inproceedings{shipman1999beyond, acmid = {294498}, address = {New York, NY, USA}, author = {{Shipman, III}, Frank M. and Marshall, Catherine C. and LeMere, Mark}, booktitle = {Proceedings of the tenth ACM Conference on Hypertext and hypermedia : returning to our diverse roots: returning to our diverse roots}, doi = {10.1145/294469.294498}, interhash = {af9b4a36c9dfe926d433aa88aea22573}, intrahash = {edf6ad72b8b8caa5dccd8219bc0ea498}, isbn = {1-58113-064-3}, location = {Darmstadt, Germany}, numpages = {10}, pages = {121--130}, publisher = {ACM}, title = {Beyond location: hypertext workspaces and non-linear views}, url = {http://doi.acm.org/10.1145/294469.294498}, year = 1999 } @incollection{stumme1998conceptual, abstract = {In this paper we discuss Conceptual Knowledge Discovery in Databases (CKDD) as it is developing in the field of Conceptual Knowledge Processing (cf. [29],[30]). Conceptual Knowledge Processing is based on the mathematical theory of Formal Concept Analysis which has become a successful theory for data analysis during the last 18 years. This approach relies on the pragmatic philosophy of Ch.S. Peirce [15] who claims that we can only analyze and argue within restricted contexts where we always rely on pre-knowledge and common sense. The development of Formal Concept Analysis led to the software system TOSCANA, which is presented as a CKDD tool in this paper. TOSCANA is a flexible navigation tool that allows dynamic browsing through and zooming into the data. It supports the exploration of large databases by visualizing conceptual aspects inherent to the data. We want to clarify that CKDD can be understood as a human-centered approach of Knowledge Discovery in Databases. The actual discussion about human-centered Knowledge Discovery is therefore briefly summarized in Section 1.}, address = {Berlin/Heidelberg}, affiliation = {Technische Universität Darmstadt Fachbereich Mathematik D-64289 Darmstadt Germany D-64289 Darmstadt Germany}, author = {Stumme, Gerd and Wille, Rudolf and Wille, Uta}, booktitle = {Principles of Data Mining and Knowledge Discovery}, doi = {10.1007/BFb0094849}, editor = {Zytkow, Jan and Quafafou, Mohamed}, interhash = {5ef89b6f8fb22f9d24eda7da71b8bdb1}, intrahash = {a9859c988f19684b76dc5a3f24e8278e}, isbn = {978-3-540-65068-3}, keyword = {Computer Science}, pages = {450--458}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Conceptual Knowledge Discovery in Databases using formal concept analysis methods}, url = {http://dx.doi.org/10.1007/BFb0094849}, volume = 1510, year = 1998 }