@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{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 } @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{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 } @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 } @article{adomavicius2012impact, abstract = {This article investigates the impact of rating data characteristics on the performance of several popular recommendation algorithms, including user-based and item-based collaborative filtering, as well as matrix factorization. We focus on three groups of data characteristics: rating space, rating frequency distribution, and rating value distribution. A sampling procedure was employed to obtain different rating data subsamples with varying characteristics; recommendation algorithms were used to estimate the predictive accuracy for each sample; and linear regression-based models were used to uncover the relationships between data characteristics and recommendation accuracy. Experimental results on multiple rating datasets show the consistent and significant effects of several data characteristics on recommendation accuracy.}, acmid = {2151166}, address = {New York, NY, USA}, articleno = {3}, author = {Adomavicius, Gediminas and Zhang, Jingjing}, doi = {10.1145/2151163.2151166}, interhash = {53e424cc9502ebb33d38de1d04230196}, intrahash = {e41453a56391ca382f2298607b361208}, issn = {2158-656X}, issue_date = {April 2012}, journal = {ACM Trans. Manage. Inf. Syst.}, month = apr, number = 1, numpages = {17}, pages = {3:1--3:17}, publisher = {ACM}, title = {Impact of Data Characteristics on Recommender Systems Performance}, url = {http://doi.acm.org/10.1145/2151163.2151166}, volume = 3, year = 2012 } @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 } @inproceedings{narayanan2008robust, 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. We apply our de-anonymization methodology to the Netflix Prize dataset, which contains anonymous movie ratings of 500,000 subscribers of Netflix, the world's largest online movie rental service. We demonstrate that an adversary who knows only a little bit about an individual subscriber can easily identify this subscriber's record in the dataset. Using the Internet Movie Database as the source of background knowledge, we successfully identified the Netflix records of known users, uncovering their apparent political preferences and other potentially sensitive information.}, author = {Narayanan, Arvind and Shmatikov, Vitaly}, booktitle = {Proc. of the 29th IEEE Symposium on Security and Privacy}, doi = {10.1109/SP.2008.33}, interhash = {77c86be6c4bf7fc51b7faecfe85479fe}, intrahash = {2748ba4684dbe09120aee56c6a0a9de9}, issn = {1081-6011}, month = may, pages = {111--125}, publisher = {IEEE Computer Society}, title = {Robust De-anonymization of Large Sparse Datasets}, url = {http://www.cs.utexas.edu/~shmat/shmat_oak08netflix.pdf}, year = 2008 } @article{larowe2009scholarly, abstract = {The Scholarly Database aims to serve researchers and practitioners interested in the analysis, modelling, and visualization of large-scale data sets. A specific focus of this database is to support macro-evolutionary studies of science and to communicate findings via knowledge-domain visualizations. Currently, the database provides access to about 18 million publications, patents, and grants. About 90% of the publications are available in full text. Except for some datasets with restricted access conditions, the data can be retrieved in raw or pre-processed formats using either a web-based or a relational database client. This paper motivates the need for the database from the perspective of bibliometric/scientometric research. It explains the database design, setup, etc., and reports the temporal, geographical, and topic coverage of data sets currently served via the database. Planned work and the potential for this database to become a global testbed for information science research are discussed at the end of the paper.}, author = {La Rowe, Gavin and Ambre, Sumeet and Burgoon, John and Ke, Weimao and Börner, Katy}, doi = {10.1007/s11192-009-0414-2}, interhash = {1819f263b0ea1b99ec15d0c22b38207e}, intrahash = {c24611ec1f2efbdcf7f5b26d49af320e}, issn = {0138-9130}, journal = {Scientometrics}, language = {English}, number = 2, pages = {219--234}, publisher = {Springer Netherlands}, title = {The Scholarly Database and its utility for scientometrics research}, url = {http://dx.doi.org/10.1007/s11192-009-0414-2}, volume = 79, year = 2009 } @inproceedings{liu2006web, author = {Liu, Vinci and Curran, James R.}, booktitle = {EACL}, crossref = {conf/eacl/2006}, ee = {http://acl.ldc.upenn.edu/E/E06/E06-1030.pdf}, interhash = {f966023df4185e781314340265d3df1f}, intrahash = {934a38bd8d7696cff1da3a2df3724407}, isbn = {1-932432-59-0}, publisher = {The Association for Computer Linguistics}, title = {Web Text Corpus for Natural Language Processing.}, url = {http://dblp.uni-trier.de/db/conf/eacl/eacl2006.html#LiuC06}, year = 2006 }