@article{McRae:2005:Behav-Res-Methods:16629288, title = {Semantic feature production norms for a large set of living and nonliving things}, author = {K McRae and G S Cree and M S Seidenberg and C McNorgan}, journal = {Behav Res Methods}, month = {Nov}, number = 4, pages = {547-559}, volume = 37, year = 2005, url = {http://www.ncbi.nlm.nih.gov/pubmed/16629288}, pmid = {16629288}, description = {Semantic feature production norms for a large set ...[Behav Res Methods. 2005] - PubMed Result}, abstract = {Semantic features have provided insight into numerous behavioral phenomena concerning concepts, categorization, and semantic memory in adults, children, and neuropsychological populations. Numerous theories and models in these areas are based on representations and computations involving semantic features. Consequently, empirically derived semantic feature production norms have played, and continue to play, a highly useful role in these domains. This article describes a set of feature norms collected from approximately 725 participants for 541 living (dog) and nonliving (chair) basic-level concepts, the largest such set of norms developed to date. This article describes the norms and numerous statistics associated with them. Our aim is to make these norms available to facilitate other research, while obviating the need to repeat the labor-intensive methods involved in collecting and analyzing such norms. The full set of norms may be downloaded from www.psychonomic.org/archive.}, biburl = {http://www.bibsonomy.org/bibtex/2936af12b025e37b0a6aac6bc103f58a3/hotho}, keywords = {dataset grounding ol ontology relation semantic toread} } @inproceedings{cone2006, title = {Cone Cluster Labeling for Support Vector Clustering}, author = {Sei-Hyung Lee and Karen M. Daniels}, booktitle = {Proceedings of 6th SIAM Conference on Data Mining}, month = {May}, pages = {484–488}, year = 2006, url = {http://www.siam.org/meetings/sdm06/proceedings/046lees.pdf}, added = {2007-04-29 16:58:13 +0200}, modified = {2007-06-19 18:52:22 +0200}, description = {BibSonomy::edit bibtex}, biburl = {http://www.bibsonomy.org/bibtex/276d1018ba398695e454d20de302de6e6/hotho}, keywords = {SVM clustering code toread} } @article{Lerman:2007p3955, title = {Social Information Processing in Social News Aggregation}, author = {Kristina Lerman}, journal = {arXiv}, month = {Jan}, year = 2007, url = {http://arxiv.org/abs/cs.CY/0703087}, pmid = {11330701288966819101related:HY3tKMq8Pp0J}, added = {2008-02-07 01:06:26 +0100}, read = {Yes}, rating = {0}, uri = {papers://C3B117CD-23C4-4854-9426-AC96AFB113DA/Paper/p3955}, url = {file://localhost/Users/bertilhatt/Documents/Papers/Lerman/2007/Lerman%202007%20arXiv.pdf}, modified = {2008-02-07 02:25:10 +0100}, description = {March 2008}, abstract = {The rise of the social media sites, such as blogs, wikis, Digg and Flickr among others, underscores the transformation of the Web to a participatory medium in which users are collaboratively creating, evaluating and distributing information. The innovations introduced by social media has lead to a new paradigm for interacting with information, what we call 'social information processing'. In this paper, we study how social news aggregator Digg exploits social information processing to solve the problems of document recommendation and rating. First, we show, by tracking stories over time, that social networks play an important role in document recommendation. The second contribution of this paper consists of two mathematical models. The first model describes how collaborative rating and promotion of stories emerges from the independent decisions made by many users. The second model describes how a user's influence, the number of promoted stories and the user's social network, changes in time. We find qualitative agreement between predictions of the model and user data gathered from Digg.}, biburl = {http://www.bibsonomy.org/bibtex/27a080f640fa62fc81e73b9fab1e7447c/hotho}, keywords = {digg dynamics flickr network social toread} } @inproceedings{1281269, title = {A framework for community identification in dynamic social networks}, address = {New York, NY, USA}, author = {Chayant Tantipathananandh and Tanya Berger-Wolf and David Kempe}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, pages = {717--726}, publisher = {ACM}, year = 2007, url = {http://portal.acm.org/citation.cfm?doid=1281192.1281269}, location = {San Jose, California, USA}, isbn = {978-1-59593-609-7}, doi = {http://doi.acm.org/10.1145/1281192.1281269}, description = {A framework for community identification in dynamic social networks}, biburl = {http://www.bibsonomy.org/bibtex/227a4fb58300979d4dbe94e75422418bd/hotho}, keywords = {clustering community detection graph toread} } @inproceedings{Chakrabarti:2004, title = {R-MAT: A Recursive Model for Graph Mining}, author = {D. Chakrabarti and Y. Zhan and C. Faloutsos}, booktitle = {SIAM International Conference on Data Mining}, year = 2004, url = {http://www.cs.cmu.edu/~christos/PUBLICATIONS/siam04.pdf}, biburl = {http://www.bibsonomy.org/bibtex/25e5cc221d7da719909f3bf8c507b0afc/hotho}, keywords = {graph mining model toread} } @inproceedings{OsinskiSW04, title = {Lingo: Search Results Clustering Algorithm Based on Singular Value Decomposition}, author = {Stanislaw Osinski and Jerzy Stefanowski and Dawid Weiss}, booktitle = {Intelligent Information Systems}, crossref = {ConfIis2004}, pages = {359-368}, year = 2004, description = {DBLP Record 'conf/iis/OsinskiSW04'}, biburl = {http://www.bibsonomy.org/bibtex/240aba631c1ac8819bd64b0ee74bfdd1b/hotho}, keywords = {clustering lsi svd toread} } @article{wu07, title = {Novelty and collective attention}, author = {F. Wu and B. A. Huberman}, journal = {Proc. Natl. Acad. Sci. USA}, number = 45, pages = {17599-17601}, volume = 104, year = 2007, url = {http://www.pnas.org/cgi/reprint/104/45/17599.pdf}, doi = {10.1073/pnas.0704916104}, eprint = {http://www.pnas.org/cgi/reprint/104/45/17599.pdf}, description = {Novelty and collective attention -- Wu and Huberman 104 (45): 17599 -- Proceedings of the National Academy of Sciences}, abstract = {The subject of collective attention is central to an information age where millions of people are inundated with daily messages. It is thus of interest to understand how attention to novel items propagates and eventually fades among large populations. We have analyzed the dynamics of collective attention among 1 million users of an interactive web site, digg.com, devoted to thousands of novel news stories. The observations can be described by a dynamical model characterized by a single novelty factor. Our measurements indicate that novelty within groups decays with a stretched-exponential law, suggesting the existence of a natural time scale over which attention fades. }, biburl = {http://www.bibsonomy.org/bibtex/2ff0a7c4758b8bfdf5cf117f652884728/hotho}, keywords = {attention collective folksonomy novelty toread} } @inproceedings{Approximating2008Java, title = {Approximating the Community Structure of the Long Tail}, author = {Akshay Java and Anupam Joshi and Tim FininBook}, booktitle = {Proceedings of the Second International Conference on Weblogs and Social Media(ICWSM 2008)}, publisher = {AAAI Press}, year = 2008, url = {http://ebiquity.umbc.edu/paper/html/id/381/Approximating-the-Community-Structure-of-the-Long-Tail}, date = {2008 Abstract:}, description = {Approximating the Community Structure of the Long Tail}, abstract = {In many social media applications, a small fraction of the members are highly linked while most are sparsely connected to the network. Such a skewed distribution is sometimes referred to as the"long tail". Popular applications like meme trackers and content aggregators mine for information from only the popular blogs located at the head of this curve. On the other hand, the long tail contains large volumes of interesting information and niches. The question we address in this work is how best to approximate the community membership of entities in the long tail using only a small percentage of the entire graph structure. Our technique utilizes basic linear algebra manipulations and spectral methods. It has the advantage of quickly and efficiently finding a reasonable approximation of the community structure of the overall network. Such a method has significant applications in blog analysis engines as well as social media monitoring tools in general. }, biburl = {http://www.bibsonomy.org/bibtex/2386f36679c111f30e37ced272d5b355c/hotho}, keywords = {clustering community detection svd toread} } @article{kostoff, title = {Literature-related discovery (LRD): Potential treatments for cataracts}, author = {Ronald N. Kostoff}, journal = {Technological Forecasting and Social Change}, pages = {--}, volume = {In Press, Corrected Proof}, year = 2007, url = {http://www.sciencedirect.com/science/article/B6V71-4RDB8SC-9/2/8991fe8968a0ef12f22ed7e9ac9d7c4f}, description = {ScienceDirect - Technological Forecasting and Social Change : Literature-related discovery (LRD): Potential treatments for cataracts}, abstract = {Literature-related discovery (LRD) is the linking of two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge (i.e., potential discovery). The open discovery systems (ODS) component of LRD starts with a problem to be solved, and generates solutions to that problem through potential discovery. We have been using ODS LRD to identify potential treatments or preventative actions for challenging medical problems, among myriad other applications. This paper describes the second medical problem we addressed (cataract) using ODS LRD; the first problem addressed was Raynaud's Phenomenon (RP), and was described in the third paper of this Special Issue. Cataract was selected because it is ubiquitous globally, appears intractable to all forms of treatment other than surgical removal of cataracts, and is a major cause of blindness in many developing countries. The ODS LRD study had three objectives: a) identify non-drug non-surgical treatments that would 1) help prevent cataracts, or 2) reduce the progression rate of cataracts, or 3) stop the progression of cataracts, or 4) maybe even reverse the progression of cataracts; b) demonstrate that we could solve an ODS LRD problem with no prior knowledge of any results or prior work (unlike the case with the RP problem); c) determine whether large time savings in the discovery process were possible relative to the time required for conducting the RP study. To that end, we used the MeSH taxonomy of MEDLINE to restrict potential discoveries to selected semantic classes, as a substitute for the manually-intensive process used in the RP study to restrict potential discoveries to selected semantic classes. We also used additional semantic filtering to identify potential discovery within the selected semantic classes. All these goals were achieved. As will be shown, we generated large amounts of potential discovery in more than an order of magnitude less time than required for the RP study. We identified many non-drug non-surgical treatments that may be able to reduce or even stop the progression rate of cataracts. Time, and much testing, will determine whether this is possible. Finally, the methodology has been developed to the point where ODS LRD problems can be solved with no results or knowledge of any prior work.}, biburl = {http://www.bibsonomy.org/bibtex/2b9359f79985da9b9677340ffda849e74/hotho}, keywords = {clustering discovery mining retrieval semantic text toread} } @article{isafolksonomy2007fwn, title = {{Folksonomies: Why do we need controlled vocabulary?}}, author = {Alireza Noruzi}, journal = {Webology}, number = 2, volume = 4, year = 2007, url = {http://www.webology.ir/2007/v4n2/editorial12.html}, biburl = {http://www.bibsonomy.org/bibtex/2eaef17fef76ad3152f0300a5e9d5ddae/hotho}, keywords = {controlled folksonomy ontology toread vocabulary} }