@article{grimmer2013text, author = {Grimmer, Justin and Stewart, Brandon M}, interhash = {eb68e01ef4168a398d79f408042fe529}, intrahash = {76001ebc726700bef81886d2e285b7cf}, journal = {Political Analysis}, pages = {mps028}, publisher = {SPM-PMSAPSA}, title = {Text as data: The promise and pitfalls of automatic content analysis methods for political texts}, year = 2013 } @article{SSQU:SSQU478, abstract = {Objective. This study is an effort to produce a more systematic, empirically-based, historical-comparative understanding of media bias than generally is found in previous works.Methods. The research employs a quantitative measure of ideological bias in a formal content analysis of the United States' two largest circulation news magazines, Time and Newsweek. Findings are compared with the results of an identical examination of two of the nation's leading partisan journals, the conservative National Review and the liberal Progressive.Results. Bias scores reveal stark differences between the mainstream and the partisan news magazines' coverage of four issue areas: crime, the environment, gender, and poverty.Conclusion. Data provide little support for those claiming significant media bias in either ideological direction.}, author = {Covert, Tawnya J. Adkins and Wasburn, Philo C.}, doi = {10.1111/j.1540-6237.2007.00478.x}, interhash = {9276222b3b8684048db1e42c3a9f3409}, intrahash = {81474f00e1605d45462e23f743dc88bb}, issn = {1540-6237}, journal = {Social Science Quarterly}, number = 3, pages = {690--706}, publisher = {Blackwell Publishing Inc}, title = {Measuring Media Bias: A Content Analysis of Time and Newsweek Coverage of Domestic Social Issues, 1975–2000*}, url = {http://dx.doi.org/10.1111/j.1540-6237.2007.00478.x}, volume = 88, year = 2007 } @inproceedings{lorince2014supertagger, author = {Lorince, Jared and Zorowitz, Sam and Murdock, Jaimie and Todd, Peter}, interhash = {4af29810e9c882dc18f560527c65de2f}, intrahash = {014abc7dc30e38859c5e8605dce1a8f6}, title = {“Supertagger” Behavior in Building Folksonomies}, year = 2014 } @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{Laniado2010, author = {Laniado, David and Mika, Peter}, booktitle = {International Semantic Web Conference (1)}, crossref = {conf/semweb/2010-1}, editor = {Patel-Schneider, Peter F. and Pan, Yue and Hitzler, Pascal and Mika, Peter and Zhang, Lei and Pan, Jeff Z. and Horrocks, Ian and Glimm, Birte}, ee = {http://dx.doi.org/10.1007/978-3-642-17746-0_30}, interhash = {3a63f88e11f958d548fa91fe442e1dcf}, intrahash = {58dace4881efbd12c81ef1cc2e6bf7b9}, isbn = {978-3-642-17745-3}, pages = {470-485}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Making Sense of Twitter.}, url = {http://dblp.uni-trier.de/db/conf/semweb/iswc2010-1.html#LaniadoM10}, volume = 6496, 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{Keally:2011:PTP:2070942.2070968, abstract = {The vast array of small wireless sensors is a boon to body sensor network applications, especially in the context awareness and activity recognition arena. However, most activity recognition deployments and applications are challenged to provide personal control and practical functionality for everyday use. We argue that activity recognition for mobile devices must meet several goals in order to provide a practical solution: user friendly hardware and software, accurate and efficient classification, and reduced reliance on ground truth. To meet these challenges, we present PBN: Practical Body Networking. Through the unification of TinyOS motes and Android smartphones, we combine the sensing power of on-body wireless sensors with the additional sensing power, computational resources, and user-friendly interface of an Android smartphone. We provide an accurate and efficient classification approach through the use of ensemble learning. We explore the properties of different sensors and sensor data to further improve classification efficiency and reduce reliance on user annotated ground truth. We evaluate our PBN system with multiple subjects over a two week period and demonstrate that the system is easy to use, accurate, and appropriate for mobile devices.}, acmid = {2070968}, address = {New York, NY, USA}, author = {Keally, Matthew and Zhou, Gang and Xing, Guoliang and Wu, Jianxin and Pyles, Andrew}, booktitle = {Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems}, doi = {10.1145/2070942.2070968}, interhash = {5e6a13d34026f65338cfa619054822c8}, intrahash = {61e5e4559d031c4152b3f316c0aa5209}, isbn = {978-1-4503-0718-5}, location = {Seattle, Washington}, numpages = {14}, pages = {246--259}, publisher = {ACM}, series = {SenSys '11}, title = {PBN: towards practical activity recognition using smartphone-based body sensor networks}, url = {http://doi.acm.org/10.1145/2070942.2070968}, year = 2011 } @misc{Kim2012, abstract = { Sentiment analysis predicts the presence of positive or negative emotions in a text document. In this paper we consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a finite set of human emotions. We investigate the resulting model, compare it to psychological observations, and explore its predictive capabilities. Besides obtaining significant improvements over a baseline without manifold, we are also able to visualize different notions of positive sentiment in different domains. }, author = {Kim, Seungyeon and Li, Fuxin and Lebanon, Guy and Essa, Irfan}, interhash = {78c5eda9e1ef2780d70234dc4942203f}, intrahash = {d169c08d5241a0912f3d60c97d87e2c0}, note = {cite arxiv:1202.1568Comment: 15 pages, 7 figures}, title = {Beyond Sentiment: The Manifold of Human Emotions}, url = {http://arxiv.org/abs/1202.1568}, year = 2012 } @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 } @inproceedings{Bethard:2010:ICL:1871437.1871517, 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 = {http://doi.acm.org/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}, series = {CIKM '10}, title = {Who should I cite: learning literature search models from citation behavior}, url = {http://doi.acm.org/10.1145/1871437.1871517}, year = 2010 } @inproceedings{anagnostopoulos2011authority, author = {Anagnostopoulos, Aris and Brova, George and Terzi, Evimaria}, booktitle = {Proceedings of the ECML/PKDD 2011}, interhash = {4b69d0de5d0c542404c9eb387abb0ac2}, intrahash = {eb4553d07c2975a62fff33e92646a7df}, title = {Peer and Authority Pressure in Information-Propagation Models}, year = 2011 } @inproceedings{cattuto2007vocabulary, abstract = { We analyze a large-scale snapshot of del.icio.us and investigate how the number of different tags in the system grows as a function of a suitably defined notion of time. We study the temporal evolution of the global vocabulary size, i.e. the number of distinct tags in the entire system, as well as the evolution of local vocabularies, that is the growth of the number of distinct tags used in the context of a given resource or user. In both cases, we find power-law behaviors with exponents smaller than one. Surprisingly, the observed growth behaviors are remarkably regular throughout the entire history of the system and across very different resources being bookmarked. Similar sub-linear laws of growth have been observed in written text, and this qualitative universality calls for an explanation and points in the direction of non-trivial cognitive processes in the complex interaction patterns characterizing collaborative tagging.}, author = {Cattuto, Ciro and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio}, interhash = {7de017393b2d48335e209a9db23e08b6}, intrahash = {fb163dd424fa1eb40640340f27ee0ea4}, title = {Vocabulary growth in collaborative tagging systems}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:0704.3316}, year = 2007 } @inproceedings{baezayates2007extracting, abstract = {In this paper we study a large query log of more than twenty million queries with the goal of extracting the semantic relations that are implicitly captured in the actions of users submitting queries and clicking answers. Previous query log analyses were mostly done with just the queries and not the actions that followed after them. We first propose a novel way to represent queries in a vector space based on a graph derived from the query-click bipartite graph. We then analyze the graph produced by our query log, showing that it is less sparse than previous results suggested, and that almost all the measures of these graphs follow power laws, shedding some light on the searching user behavior as well as on the distribution of topics that people want in the Web. The representation we introduce allows to infer interesting semantic relationships between queries. Second, we provide an experimental analysis on the quality of these relations, showing that most of them are relevant. Finally we sketch an application that detects multitopical URLs.}, address = {New York, NY, USA}, author = {Baeza-Yates, Ricardo and Tiberi, Alessandro}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, doi = {http://doi.acm.org/10.1145/1281192.1281204}, file = {baezayates2007extracting.pdf:baezayates2007extracting.pdf:PDF}, groups = {public}, interhash = {26ca034be705abaf072835784f53d877}, intrahash = {6e45b65feffd1545c6dca62bf4b8f53d}, isbn = {978-1-59593-609-7}, location = {San Jose, California, USA}, pages = {76--85}, publisher = {ACM}, timestamp = {2009-06-01 15:31:03}, title = {Extracting semantic relations from query logs}, url = {http://portal.acm.org/citation.cfm?id=1281192.1281204}, username = {dbenz}, year = 2007 } @article{journals/www/EdaYUU09, author = {Eda, Takeharu and Yoshikawa, Masatoshi and Uchiyama, Toshio and Uchiyama, Tadasu}, ee = {http://dx.doi.org/10.1007/s11280-009-0069-1}, interhash = {a560796c977bc7582017f662bf88c16d}, intrahash = {ec3c256e7d1f24cd9d407d3ce7e41d96}, journal = {World Wide Web}, number = 4, pages = {421-440}, title = {The Effectiveness of Latent Semantic Analysis for Building Up a Bottom-up Taxonomy from Folksonomy Tags.}, url = {http://dblp.uni-trier.de/db/journals/www/www12.html#EdaYUU09}, volume = 12, year = 2009 } @article{mislove2007measurement, author = {Mislove, A. and Marcon, M. and Gummadi, K.P. and Druschel, P. and Bhattacharjee, B.}, booktitle = {Proceedings of the 7th ACM SIGCOMM conference on Internet measurement}, interhash = {cb29c839ea0b125778ae58934f35082f}, intrahash = {aa568938d581a2885e7898e4852ee62f}, organization = {ACM}, pages = 42, title = {{Measurement and analysis of online social networks}}, url = {http://scholar.google.de/scholar.bib?q=info:HmucgVkM3hQJ:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=0}, year = 2007 } @inproceedings{1150476, abstract = {In this paper, we consider the evolution of structure within large online social networks. We present a series of measurements of two such networks, together comprising in excess of five million people and ten million friendship links, annotated with metadata capturing the time of every event in the life of the network. Our measurements expose a surprising segmentation of these networks into three regions: singletons who do not participate in the network; isolated communities which overwhelmingly display star structure; and a giant component anchored by a well-connected core region which persists even in the absence of stars.We present a simple model of network growth which captures these aspects of component structure. The model follows our experimental results, characterizing users as either passive members of the network; inviters who encourage offline friends and acquaintances to migrate online; and linkers who fully participate in the social evolution of the network.}, address = {New York, NY, USA}, author = {Kumar, Ravi and Novak, Jasmine and Tomkins, Andrew}, booktitle = {KDD '06: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining}, doi = {http://doi.acm.org/10.1145/1150402.1150476}, interhash = {d3729a29d377e03b31c80bcc58843681}, intrahash = {03874e666c56f22bce1b7db254420d77}, isbn = {1-59593-339-5}, location = {Philadelphia, PA, USA}, pages = {611--617}, publisher = {ACM}, title = {Structure and evolution of online social networks}, url = {http://portal.acm.org/citation.cfm?id=1150402.1150476}, year = 2006 } @article{broder2000graph, author = {Broder, A. and Kumar, R. and Maghoul, F. and Raghavan, P. and Rajagopalan, S. and Stata, R. and Tomkins, A. and Wiener, J.}, interhash = {98795b0cdfa813f7dcc49723c426634d}, intrahash = {2bacaf21af433dbad4c6574bf726e5fd}, journal = {Computer Networks}, number = {1-6}, pages = {309--320}, publisher = {Elsevier}, title = {{Graph structure in the web}}, url = {http://scholar.google.de/scholar.bib?q=info:XK3rB5QCtqgJ:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=0}, volume = 33, year = 2000 } @article{Almendral2007675, abstract = {We use the emergent field of complex networks to analyze the network of scientific collaborations between entities (universities, research organizations, industry related companies,...) which collaborate in the context of the so-called framework programme. We demonstrate here that it is a scale-free network with an accelerated growth, which implies that the creation of new collaborations is encouraged. Moreover, these collaborations possess hierarchical modularity. Likewise, we find that the information flow depends on the size of the participants but not on geographical constraints.}, author = {Almendral, Juan A. and Oliveira, J.G. and López, L. and Mendes, J.F.F. and Sanjuán, Miguel A.F.}, doi = {DOI: 10.1016/j.physa.2007.05.049}, interhash = {999b6173bf61181a3ec70b140af51009}, intrahash = {5e2201924073d4b98c68f9d23c171f41}, issn = {0378-4371}, journal = {Physica A: Statistical Mechanics and its Applications}, number = 2, pages = {675 - 683}, title = {The network of scientific collaborations within the European framework programme}, url = {http://www.sciencedirect.com/science/article/B6TVG-4NTJH10-4/2/b209f12299c9e1d367a8298e7d986215}, volume = 384, year = 2007 }