@article{shannon1951prediction, author = {Shannon, Claude Elwood}, interhash = {daabc21c7f6e71f6e78a10c8d3492927}, intrahash = {2e79cf0f6022645a632b13e081b0b035}, journal = {Bell System Technical Journal}, month = jan, pages = {50--64}, title = {Prediction and Entropy of Printed English}, url = {http://languagelog.ldc.upenn.edu/myl/Shannon1950.pdf}, volume = 30, year = 1951 } @article{shannon1948mathematical, author = {Shannon, Claude E.}, interhash = {754130207906fcec16a53d330eeff348}, intrahash = {b6bc42c140f0147cd6a1781d75fcb897}, journal = {The Bell System Technical Journal}, month = {July, October}, pages = {379--423, 623--656}, title = {A Mathematical Theory of Communication}, url = {http://cm.bell-labs.com/cm/ms/what/shannonday/shannon1948.pdf}, volume = 27, year = 1948 } @inproceedings{pfaltz2012entropy, abstract = {We introduce the concepts of closed sets and closure operators as mathematical tools for the study of social networks. Dynamic networks are represented by transformations. It is shown that under continuous change/transformation, all networks tend to "break down" and become less complex. It is a kind of entropy. The product of this theoretical decomposition is an abundance of triadically closed clusters which sociologists have observed in practice. This gives credence to the relevance of this kind of mathematical analysis in the sociological context. }, author = {Pfaltz, John L.}, booktitle = {Proceedings of the SOCINFO}, interhash = {753f13a5ffaa0946220164c2b05c230f}, intrahash = {044d0b1f6e737bede270a40bbddb0b06}, title = {Entropy in Social Networks}, year = 2012 } @article{birkholz2012scalable, abstract = {Studies on social networks have proved that endogenous and exogenous factors influence dynamics. Two streams of modeling exist on explaining the dynamics of social networks: 1) models predicting links through network properties, and 2) models considering the effects of social attributes. In this interdisciplinary study we work to overcome a number of computational limitations within these current models. We employ a mean-field model which allows for the construction of a population-specific socially informed model for predicting links from both network and social properties in large social networks. The model is tested on a population of conference coauthorship behavior, considering a number of parameters from available Web data. We address how large social networks can be modeled preserving both network and social parameters. We prove that the mean-field model, using a data-aware approach, allows us to overcome computational burdens and thus scalability issues in modeling large social networks in terms of both network and social parameters. Additionally, we confirm that large social networks evolve through both network and social-selection decisions; asserting that the dynamics of networks cannot singly be studied from a single perspective but must consider effects of social parameters. }, author = {Birkholz, Julie M. and Bakhshi, Rena and Harige, Ravindra and van Steen, Maarten and Groenewegen, Peter}, interhash = {a8ef0aac2eab74fc8eb3f9d3dc8a32dd}, intrahash = {aefcc2aa922b048bec85d5070494ed81}, journal = {CoRR}, month = sep, title = {Scalable Analysis of Socially Informed Network Models: the data-aware mean-field approach }, url = {http://arxiv.org/abs/1209.6615}, volume = {abs/1209.6615}, year = 2012 } @inproceedings{chai2009efficiently, abstract = {Many applications increasingly employ information extraction and integration (IE/II) programs to infer structures from unstructured data. Automatic IE/II are inherently imprecise. Hence such programs often make many IE/II mistakes, and thus can significantly benefit from user feedback. Today, however, there is no good way to automatically provide and process such feedback. When finding an IE/II mistake, users often must alert the developer team (e.g., via email or Web form) about the mistake, and then wait for the team to manually examine the program internals to locate and fix the mistake, a slow, error-prone, and frustrating process.

In this paper we propose a solution for users to directly provide feedback and for IE/II programs to automatically process such feedback. In our solution a developer U uses hlog, a declarative IE/II language, to write an IE/II program P. Next, U writes declarative user feedback rules that specify which parts of P's data (e.g., input, intermediate, or output data) users can edit, and via which user interfaces. Next, the so-augmented program P is executed, then enters a loop of waiting for and incorporating user feedback. Given user feedback F on a data portion of P, we show how to automatically propagate F to the rest of P, and to seamlessly combine F with prior user feedback. We describe the syntax and semantics of hlog, a baseline execution strategy, and then various optimization techniques. Finally, we describe experiments with real-world data that demonstrate the promise of our solution.}, acmid = {1559857}, address = {New York, NY, USA}, author = {Chai, Xiaoyong and Vuong, Ba-Quy and Doan, AnHai and Naughton, Jeffrey F.}, booktitle = {Proceedings of the 35th SIGMOD international conference on Management of data}, doi = {10.1145/1559845.1559857}, interhash = {5860215447e374b059597c0e3864e388}, intrahash = {d6c9fbf442a935dc0618107f8fb54d44}, isbn = {978-1-60558-551-2}, location = {Providence, Rhode Island, USA}, numpages = {14}, pages = {87--100}, publisher = {ACM}, title = {Efficiently incorporating user feedback into information extraction and integration programs}, url = {http://doi.acm.org/10.1145/1559845.1559857}, year = 2009 } @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{chan2009mathematical, abstract = {Human computation is a technique that makes use of human abilities for computation to solve problems. Social games use the power of the Internet game players to solve human computation problems. In previous works, many social games were proposed and were quite successful, but no formal framework exists for designing social games in general. A formal framework is important because it lists out the design elements of a social game, the characteristics of a human computation problem, and their relationships. With a formal framework, it simplifies the way to design a social game for a specific problem. In this paper, our contributions are: (1) formulate a formal model on social games, (2) analyze the framework and derive some interesting properties based on model's interactions, (3) illustrate how some current social games can be realized with the proposed formal model, and (4) describe how to design a social game for solving a specific problem with the use of the proposed formal model. This paper presents a set of design guidelines derived from the formal model and demonstrates that the model can help to design a social game for solving a specific problem in a formal and structural way.}, author = {Chan, Kam Tong and King, I. and Yuen, Man-Ching}, booktitle = {Proceedings of the International Conference on Computational Science and Engineering, CSE '09}, doi = {10.1109/CSE.2009.166}, interhash = {a54732b662bcb0d763139a38f6525b56}, intrahash = {216d582316e970eb498423ee8448edbe}, month = aug, pages = {1205--1210}, title = {Mathematical Modeling of Social Games}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5283086&tag=1}, volume = 4, year = 2009 } @book{feller1968introduction, address = {New York}, author = {Feller, William}, interhash = {5913bc93a52c1fad7ce8b0993debf407}, intrahash = {cf464e5e44fbad2b68e11a80cbded06e}, isbn = {0-471-25708-7}, publisher = {Wiley}, title = {An introduction to probability theory and its applications}, url = {http://opac.bibliothek.uni-kassel.de/DB=1/PPN?PPN=177850175}, year = 1968 } @article{golovchinsky2009collaborative, abstract = {An examination of the roles and dimensions of collaborative search reveals new opportunities for information-seeking support tools.}, author = {Golovchinsky, G. and Qvarfordt, P. and Pickens, J.}, doi = {10.1109/MC.2009.73}, interhash = {786e0e4074d14492baca93770b87bb6b}, intrahash = {3952c105cee15d5da9a50e5557f974ab}, issn = {0018-9162}, journal = {Computer}, month = {march }, number = 3, pages = {47--51}, title = {Collaborative Information Seeking}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4803888&tag=1}, volume = 42, year = 2009 } @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 } @article{evans2010elaborated, abstract = {Search engine researchers typically depict search as the solitary activity of an individual searcher. In contrast, results from our critical-incident survey of 150 users on Amazon's Mechanical Turk service suggest that social interactions play an important role throughout the search process. A second survey of also 150 users, focused instead on difficulties encountered during searches, suggests similar conclusions. These social interactions range from highly coordinated collaborations with shared goals to loosely coordinated collaborations in which only advice is sought. Our main contribution is that we have integrated models from previous work in sensemaking and information-seeking behavior to present a canonical social model of user activities before, during, and after a search episode, suggesting where in the search process both explicitly and implicitly shared information may be valuable to individual searchers. We seek to situate collaboration in these search episodes in the context of our developed model for social search. We discuss factors that influence social interactions and content sharing during search activities. We also explore the relationship between social interactions, motivations, and query needs. Finally, we introduce preliminary findings from the second survey on difficult and failed search efforts, discussing how query needs and social interactions may differ in cases of search failures.}, author = {Evans, Brynn M. and Chi, Ed H.}, doi = {10.1016/j.ipm.2009.10.012}, interhash = {5a3bc1b41dd288e1cf632f658a4d97ed}, intrahash = {90594e966a51f2f97abcb05b3c967ab4}, issn = {0306-4573}, journal = {Information Processing & Management}, number = 6, pages = {656--678}, title = {An elaborated model of social search}, url = {http://www.sciencedirect.com/science/article/pii/S0306457309001332}, volume = 46, year = 2010 } @book{lynch1992image, author = {Lynch, Kevin}, interhash = {7e2c57af8a2ba9fde0cfa4f401cdc72f}, intrahash = {2e9cc23aad987c883011884d6375dc4d}, isbn = {9780262620017}, publisher = {MIT Press}, title = {The image of the city}, url = {http://books.google.de/books?id=\_phRPWsSpAgC}, year = 1992 } @book{nold2009emotional, abstract = {Emotional Cartography is a collection of essays from artists, designers, psychogeographers, cultural researchers, futurologists and neuroscientists, brought together by Christian Nold, to explore the political, social and cultural implications of visualising intimate biometric data and emotional experiences using technology.}, author = {{Raqs Media Collective} and van de Drift, Marcel and Davis, Stephen Boyd and van Kranenburg, Rob and Hope, Sophie and Stafford, Tom}, editor = {Nold, Christian}, interhash = {8c669a3071f62b0ffe48214962e86443}, intrahash = {4610971f7f16acebe542ffe89390992e}, isbn = {978-0-9557623-1-4}, title = {Emotional Cartography - Technologies of the Self}, url = {http://emotionalcartography.net/}, year = 2009 } @book{haklay2010interacting, address = {Chichester, West Sussex, UK}, author = {Haklay, Mordechai}, interhash = {ee82b2b82e055fe1fa57c11ec1315122}, intrahash = {abd409ed5340f6563d5d82146c3e1990}, isbn = {9780470998243 0470998245}, publisher = {John Wiley}, refid = {466334086}, title = {Interacting with geospatial technologies}, url = {http://www.amazon.co.uk/gp/product/0470998245/}, year = 2010 } @article{bollen2009clickstream, abstract = {Background Intricate maps of science have been created from citation data to visualize the structure of scientific activity. However, most scientific publications are now accessed online. Scholarly web portals record detailed log data at a scale that exceeds the number of all existing citations combined. Such log data is recorded immediately upon publication and keeps track of the sequences of user requests (clickstreams) that are issued by a variety of users across many different domains. Given these advantages of log datasets over citation data, we investigate whether they can produce high-resolution, more current maps of science. Methodology Over the course of 2007 and 2008, we collected nearly 1 billion user interactions recorded by the scholarly web portals of some of the most significant publishers, aggregators and institutional consortia. The resulting reference data set covers a significant part of world-wide use of scholarly web portals in 2006, and provides a balanced coverage of the humanities, social sciences, and natural sciences. A journal clickstream model, i.e. a first-order Markov chain, was extracted from the sequences of user interactions in the logs. The clickstream model was validated by comparing it to the Getty Research Institute's Architecture and Art Thesaurus. The resulting model was visualized as a journal network that outlines the relationships between various scientific domains and clarifies the connection of the social sciences and humanities to the natural sciences. Conclusions Maps of science resulting from large-scale clickstream data provide a detailed, contemporary view of scientific activity and correct the underrepresentation of the social sciences and humanities that is commonly found in citation data.}, author = {Bollen, Johan and van de Sompel, Herbert and Hagberg, Aric and Bettencourt, Luis and Chute, Ryan and Rodriguez, Marko A. and Balakireva, Lyudmila}, doi = {10.1371/journal.pone.0004803}, interhash = {3a371a1ed31d14204770315b52023b96}, intrahash = {e61bd0c26cc1c08cff22a8301d03044f}, journal = {PLoS ONE}, month = mar, number = 3, pages = {e4803}, publisher = {Public Library of Science}, title = {Clickstream Data Yields High-Resolution Maps of Science}, url = {http://dx.doi.org/10.1371/journal.pone.0004803}, volume = 4, year = 2009 } @article{leydesdorff2012alternatives, abstract = {Journal Impact Factors (IFs) can be considered historically as the first attempt to normalize citation distributions by using averages over two years. However, it has been recognized that citation distributions vary among fields of science and that one needs to normalize for this. Furthermore, the mean-or any central-tendency statistics-is not a good representation of the citation distribution because these distributions are skewed. Important steps have been taken to solve these two problems during the last few years. First, one can normalize at the article level using the citing audience as the reference set. Second, one can use non-parametric statistics for testing the significance of differences among ratings. A proportion of most-highly cited papers (the top-10% or top-quartile) on the basis of fractional counting of the citations may provide an alternative to the current IF. This indicator is intuitively simple, allows for statistical testing, and accords with the state of the art. }, author = {Leydesdorff, Loet}, interhash = {8d14f862a94fb45d31172f8d2a6485fa}, intrahash = {bd589cc0b6fdfc74b5eea4262c46d3a4}, journal = {Digital Libraries}, title = {Alternatives to the Journal Impact Factor: I3 and the Top-10% (or Top-25%?) of the Most-Highly Cited Papers}, url = {http://arxiv.org/abs/1201.4638}, volume = {1201.4638}, year = 2012 } @book{premeaux2011arduino, abstract = { * The first Green Arduino book Walks the reader through complete environmental home projects Contains the first in-depth discussion on environmental sensors for beginners Gives hobbyists the power to make their homes green and future-proof Explains what to do with raw environmental data and how to use them in energy decision making Arduino Projects to Save the World shows that it takes little more than a few tools, a few wires and sensors, an Arduino board, and a bit of gumption to build devices that lower energy bills, help you grow our own food, monitor pollution in the air and in the ground, even warn you about earth tremors. Arduino Projects to Save the World introduces the types of sensors needed to collect environmental data—from temperature sensors to motion sensors. You'll see projects that deal with energy sources—from building your own power strip to running your Arduino board on solar panels so you can actually proceed to build systems that help, for example, to lower your energy bills. Once you have some data, it's time to put it to good use by publishing it online as you collect it; this book shows you how. The core of this book deals with the Arduino projects themselves: * Account for heat loss using a heat loss temperature sensor array that sends probes into every corner of your house for maximum measurement. * Monitor local seismic activity with your own seismic monitor. * Keep your Arduino devices alive in the field with a solar powered device that uses a smart, power-saving design. * Monitor your data and devices with a wireless radio device; place your sensors where you like without worrying about wires. * Keep an eye on your power consumption with a sophisticated power monitor that records its data wherever you like. Arduino Projects to Save the World teaches the aspiring green systems expert to build environmentally-sound, home-based Arduino devices. Saving the world, one Arduino at a time. }, author = {Premeaux, Emery and Evans, Brian}, interhash = {785564b4c2370ca578629716c9a9633a}, intrahash = {525493be3d705f9637a0b5ed0311549d}, isbn = {9781430236238 143023623X}, publisher = {Apress}, refid = {748329554}, title = {Arduino Projects to Save the World.}, url = {http://www.worldcat.org/search?qt=worldcat_org_all&q=9781430236238}, year = 2011 } @inproceedings{gaugaz2012predicting, abstract = {The amount of news content on the Web is increasing: Users can access news articles coming from a variety of sources on the Web: from newswires, news agencies, blogs, and at various places, e.g. even within Web search engines result pages. Anyhow, it still is a challenge for current search engines to decide which news events are worth being shown to the user (either for a newsworthy query or in a news portal). In this paper we define the task of predicting the future impact of news events. Being able to predict event impact will, for example, enable a newspaper to decide whether to follow a specific event or not, or a news search engine which stories to display. We define a flexible framework that, given some definition of impact, can predict its future development at the beginning of the event. We evaluate several possible definitions of event impact and experimentally identify the best features for each of them.}, author = {Gaugaz, Julien and Siehndel, Patrick and Demartini, Gianluca and Iofciu, Tereza and Georgescu, Mihai and Henze, Nicola}, booktitle = {Proc. of the 34th European Conference on Information Retrieval (ECIR 2012)}, interhash = {dc898856b5a18bf1cb9307d1bd9b5268}, intrahash = {f29c05f9a4fc3bb2189a965d95f622f9}, location = {Barcelona, Spain}, month = apr, title = {Predicting the Future Impact of News Events}, url = {http://www.l3s.de/web/page25g.do?kcond12g.att1=1833}, year = 2012 } @article{dzyubachyk2010automated, abstract = {Complete, accurate and reproducible analysis of intracellular foci from fluorescence microscopy image sequences of live cells requires full automation of all processing steps involved: cell segmentation and tracking followed by foci segmentation and pattern analysis. Integrated systems for this purpose are lacking. RESULTS: Extending our previous work in cell segmentation and tracking, we developed a new system for performing fully automated analysis of fluorescent foci in single cells. The system was validated by applying it to two common tasks: intracellular foci counting (in DNA damage repair experiments) and cell-phase identification based on foci pattern analysis (in DNA replication experiments). Experimental results show that the system performs comparably to expert human observers. Thus, it may replace tedious manual analyses for the considered tasks, and enables high-content screening. Availability and implementation: The described system was implemented in MATLAB (The MathWorks, Inc., USA) and compiled to run within the MATLAB environment. The routines together with four sample datasets are available at http://celmia.bigr.nl/. The software is planned for public release, free of charge for non-commercial use, after publication of this article.}, author = {Dzyubachyk, Oleh and Essers, Jeroen and van Cappellen, Wiggert A. and Baldeyron, Céline and Inagaki, Akiko and Niessen, Wiro J. and Meijering, Erik}, interhash = {34eafd4434352eb255bcacd995201554}, intrahash = {84abb7b420e20e5987b7f53838795af9}, journal = {Bioinformatics}, number = 19, pages = {2424-–2430}, title = {Automated analysis of time-lapse fluorescence microscopy images: from live cell images to intracellular foci}, url = {http://www.ncbi.nlm.nih.gov/pubmed/20702399}, volume = 26, year = 2010 } @inproceedings{rezel2010swefe, abstract = {This paper presents SWE-FE: a suite of methods to extend folksonomies to the worldwide Sensor Web in order to tackle the emergent data rich information poor (DRIP) syndrome afflicting most geospatial applications on the Internet. SWE-FE leverages the geospatial information associated with three key components of such collaborative tagging systems: tags, resources and users. Specifically, SWE-FE provides algorithms for: i) suggesting tags for users during the tag input stage; ii) generating tag maps which provides for serendipitous browsing; and iii) personalized searching within the folksonomy. We implement SWE-FE on the GeoCENS Sensor Web platform as a case study for assessing the efficacy of our methods. We outline the evaluation framework that we are currently employing to carry out this assessment.}, author = {Rezel, R. and Liang, S.}, booktitle = {2010 International Symposium on Collaborative Technologies and Systems (CTS)}, doi = {10.1109/CTS.2010.5478494}, interhash = {9eb696593932c517873232386f8f61bf}, intrahash = {d5b71572c7fea6504a0c0a3d84a9ecf0}, month = may, pages = {349--356}, publisher = {IEEE}, title = {SWE-FE: Extending folksonomies to the Sensor Web}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5478494}, year = 2010 }