@inproceedings{conf/www/SinhaSSMEHW15, author = {Sinha, Arnab and Shen, Zhihong and Song, Yang and Ma, Hao and Eide, Darrin and Hsu, Bo-June Paul and Wang, Kuansan}, booktitle = {WWW (Companion Volume)}, crossref = {conf/www/2015c}, editor = {Gangemi, Aldo and Leonardi, Stefano and Panconesi, Alessandro}, ee = {http://doi.acm.org/10.1145/2740908.2742839}, interhash = {6d71a6eb1d070023f6fb75a5f1019a21}, intrahash = {e6066395c31b2f3de9fb836dbac5723a}, isbn = {978-1-4503-3473-0}, pages = {243-246}, publisher = {ACM}, title = {An Overview of Microsoft Academic Service (MAS) and Applications.}, url = {http://dblp.uni-trier.de/db/conf/www/www2015c.html#SinhaSSMEHW15}, year = 2015 } @article{10.1109/TKDE.2012.115, address = {Los Alamitos, CA, USA}, author = {Zubiaga, Arkaitz and Fresno, Victor and Martinez, Raquel and Garcia-Plaza, Alberto P.}, doi = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2012.115}, interhash = {f2e961e2b99fec0634b0d4fa3e001282}, intrahash = {8a25332bfeb33e2ad8e1e1a062976da2}, issn = {1041-4347}, journal = {IEEE Transactions on Knowledge and Data Engineering}, number = {PrePrints}, publisher = {IEEE Computer Society}, title = {Harnessing Folksonomies to Produce a Social Classification of Resources}, volume = 99, year = 2012 } @inproceedings{Caverlee2008:LargeScaleStudyMySpace, author = {Caverlee, James and Webb, Steve}, booktitle = {Proceedings from the 2nd International Conference on Weblogs and Social Media (AAAI)}, comment = {"Nearly half of the profiles on MySpace have been abandoned" "While young users (in their teens and 20s) are most prevalent on MySpace, women who are most prevalent at the youngest ages (14 to 20), whereas men are most prevalent for all other ages (21 and up)." "Overall, the fraction of private profiles is increasing with time"}, interhash = {ab4c8bedf5831ad03abacd1c25b87a03}, intrahash = {56c414dfc572c2b0c5cbf48458c744b5}, posted-at = {2009-01-01 22:53:24}, priority = {2}, title = {A Large-Scale Study of MySpace: Observations and Implications for Online Social Networks}, url = {http://faculty.cs.tamu.edu/caverlee/pubs/caverlee08alarge.pdf}, year = 2008 } @inproceedings{HaHe06, abstract = {Tagging-based systems enable users to categorize web resources by means of tags (freely chosen keywords), in order to re-finding these resources later. Tagging is implicitly also a social indexing process, since users share their tags and resources, constructing a social tag index, so-called folksonomy. At the same time of tagging-based system, has been popularised an interface model for visual information retrieval known as Tag-Cloud. In this model, the most frequently used tags are displayed in alphabetical order. This paper presents a novel approach to Tag-Cloud�s tags selection, and proposes the use of clustering algorithms for visual layout, with the aim of improve browsing experience. The results suggest that presented approach reduces the semantic density of tag set, and improves the visual consistency of Tag-Cloud layout.}, author = {Hassan-Montero, Y. and Herrero-Solana, V.}, booktitle = {InScit2006: International Conference on Multidisciplinary Information Sciences and Technologies}, file = {HaHe06.pdf:folksonomies\\HaHe06.pdf:PDF}, interhash = {4458142370e3c6a4fe656af2f822a0dc}, intrahash = {06f68f9fe46dc6d0f646d932e428dec9}, misc = {comment = {proposes using k-clustering and some sort of semantic sorting to refactor tag cloud layout to improve browsing. Not clear on how they actually do it.}, priority = {0}, citeulike-article-id = {2045619}}, owner = {michael}, timestamp = {2008.01.14}, title = {Improving Tag-Clouds as Visual Information Retrieval Interfaces}, url = {http://nosolousabilidad.com/hassan/improving_tagclouds.pdf}, year = 2006 } @article{1751-8121-41-22-224016, abstract = {We analyze CiteULike, an online collaborative tagging system where users bookmark and annotate scientific papers. Such a system can be naturally represented as a tri-partite graph whose nodes represent papers, users and tags connected by individual tag assignments. The semantics of tags is studied here, in order to uncover the hidden relationships between tags. We find that the clustering coefficient can be used to analyze the semantical patterns among tags.}, author = {Capocci, Andrea and Caldarelli, Guido}, interhash = {14c8ecbc38dcdae876c3f4401006e3bb}, intrahash = {2a219a2664c566b405420f720583643a}, journal = {Journal of Physics A: Mathematical and Theoretical}, number = 22, pages = {224016 (7pp)}, title = {Folksonomies and clustering in the collaborative system CiteULike}, url = {http://stacks.iop.org/1751-8121/41/224016}, volume = 41, year = 2008 } @inproceedings{1458098, address = {New York, NY, USA}, author = {Song, Yang and Zhang, Lu and Giles, C. Lee}, booktitle = {CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge mining}, doi = {http://doi.acm.org/10.1145/1458082.1458098}, interhash = {5c03bc1e658b6d44f053944418bdaec3}, intrahash = {d330a3537b4a14fbd40661424ec8e465}, isbn = {978-1-59593-991-3}, location = {Napa Valley, California, USA}, pages = {93--102}, publisher = {ACM}, title = {A sparse gaussian processes classification framework for fast tag suggestions}, url = {http://portal.acm.org/citation.cfm?id=1458098}, year = 2008 } @article{McRae:2005:Behav-Res-Methods:16629288, 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.}, author = {McRae, K and Cree, G S and Seidenberg, M S and McNorgan, C}, interhash = {209f2874b49fd74fce1fe0ad645733e2}, intrahash = {936af12b025e37b0a6aac6bc103f58a3}, journal = {Behav Res Methods}, month = Nov, number = 4, pages = {547-559}, pmid = {16629288}, title = {Semantic feature production norms for a large set of living and nonliving things}, url = {http://www.ncbi.nlm.nih.gov/pubmed/16629288}, volume = 37, year = 2005 } @misc{narayanan-2006, abstract = { We present a new class of statistical de-anonymization attacks against high-dimensional micro-data, such as individual preferences, recommendations, transaction records and so on. Our techniques are robust to perturbation in the data and tolerate some mistakes in the adversary's background knowledge.}, author = {Narayanan, Arvind and Shmatikov, Vitaly}, interhash = {6be42821c2588b6442d6fb8ac7cd8a6e}, intrahash = {86b686a7fad55fa225123b2f79de87a8}, title = {How To Break Anonymity of the Netflix Prize Dataset}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cs/0610105}, year = 2006 } @misc{Newman+Hettich+Blake+Merz:1998, author = {Newman, C.L. Blake D.J. and Merz, C.J.}, institution = {University of California, Irvine, Dept. of Information and Computer Sciences}, interhash = {325a6b5ac5a1f044943d4298c21d31dd}, intrahash = {85308db3df761f63f16a7cab4eb8d4aa}, title = {{UCI} Repository of machine learning databases}, url = {http://www.ics.uci.edu/$\sim$mlearn/MLRepository.html}, year = 1998 }