@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}, title = {An Overview of Microsoft Academic Service (MAS) and Applications.}, editor = {Gangemi, Aldo and Leonardi, Stefano and Panconesi, Alessandro}, booktitle = {WWW (Companion Volume)}, publisher = {ACM}, year = {2015}, pages = {243-246}, url = {http://dblp.uni-trier.de/db/conf/www/www2015c.html#SinhaSSMEHW15}, isbn = {978-1-4503-3473-0}, keywords = {MSAC, dataset, toread} }

%0 = inproceedings %A = Sinha, Arnab and Shen, Zhihong and Song, Yang and Ma, Hao and Eide, Darrin and Hsu, Bo-June Paul and Wang, Kuansan %B = WWW (Companion Volume) %D = 2015 %I = ACM %T = An Overview of Microsoft Academic Service (MAS) and Applications. %U = http://dblp.uni-trier.de/db/conf/www/www2015c.html#SinhaSSMEHW15

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.

@article{adomavicius2012impact, author = {Adomavicius, Gediminas and Zhang, Jingjing}, title = {Impact of Data Characteristics on Recommender Systems Performance}, journal = {ACM Trans. Manage. Inf. Syst.}, publisher = {ACM}, address = {New York, NY, USA}, year = {2012}, volume = {3}, number = {1}, pages = {3:1--3:17}, url = {http://doi.acm.org/10.1145/2151163.2151166}, doi = {10.1145/2151163.2151166}, issn = {2158-656X}, keywords = {characteristics, dataset, dependence, evaluation, model, recommender}, 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.} }

%0 = article %A = Adomavicius, Gediminas and Zhang, Jingjing %C = New York, NY, USA %D = 2012 %I = ACM %T = Impact of Data Characteristics on Recommender Systems Performance %U = http://doi.acm.org/10.1145/2151163.2151166

@article{10.1109/TKDE.2012.115, author = {Zubiaga, Arkaitz and Fresno, Victor and Martinez, Raquel and Garcia-Plaza, Alberto P.}, title = {Harnessing Folksonomies to Produce a Social Classification of Resources}, journal = {IEEE Transactions on Knowledge and Data Engineering}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, year = {2012}, volume = {99}, number = {PrePrints}, doi = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2012.115}, issn = {1041-4347}, keywords = {classification, delicious, folksonomy, tagging, toread, dataset} }

%0 = article %A = Zubiaga, Arkaitz and Fresno, Victor and Martinez, Raquel and Garcia-Plaza, Alberto P. %C = Los Alamitos, CA, USA %D = 2012 %I = IEEE Computer Society %T = Harnessing Folksonomies to Produce a Social Classification of Resources

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.

@article{larowe2009scholarly, author = {La Rowe, Gavin and Ambre, Sumeet and Burgoon, John and Ke, Weimao and Börner, Katy}, title = {The Scholarly Database and its utility for scientometrics research}, journal = {Scientometrics}, publisher = {Springer Netherlands}, year = {2009}, volume = {79}, number = {2}, pages = {219--234}, url = {http://dx.doi.org/10.1007/s11192-009-0414-2}, doi = {10.1007/s11192-009-0414-2}, issn = {0138-9130}, keywords = {analysis, database, dataset, gaw, science, scientometrics, sdb, sota}, 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.} }

%0 = article %A = La Rowe, Gavin and Ambre, Sumeet and Burgoon, John and Ke, Weimao and Börner, Katy %D = 2009 %I = Springer Netherlands %T = The Scholarly Database and its utility for scientometrics research %U = http://dx.doi.org/10.1007/s11192-009-0414-2

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.

@article{1751-8121-41-22-224016, author = {Capocci, Andrea and Caldarelli, Guido}, title = {Folksonomies and clustering in the collaborative system CiteULike}, journal = {Journal of Physics A: Mathematical and Theoretical}, year = {2008}, volume = {41}, number = {22}, pages = {224016 (7pp)}, url = {http://stacks.iop.org/1751-8121/41/224016}, keywords = {***, citeulike, clustering, dataset, folksonomy, network, properties}, 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.} }

%0 = article %A = Capocci, Andrea and Caldarelli, Guido %D = 2008 %T = Folksonomies and clustering in the collaborative system CiteULike %U = http://stacks.iop.org/1751-8121/41/224016

@inproceedings{Caverlee2008:LargeScaleStudyMySpace, author = {Caverlee, James and Webb, Steve}, title = {A Large-Scale Study of MySpace:
servations and Implications for Online Social Networks}, booktitle = {Proceedings from the 2nd International Conference on Weblogs and Social Media (AAAI)}, year = {2008}, url = {http://faculty.cs.tamu.edu/caverlee/pubs/caverlee08alarge.pdf}, keywords = {analysis, dataset, myspace, networking, social} }

%0 = inproceedings %A = Caverlee, James and Webb, Steve %B = Proceedings from the 2nd International Conference on Weblogs and Social Media (AAAI) %D = 2008 %T = A Large-Scale Study of MySpace:
servations and Implications for Online Social Networks %U = http://faculty.cs.tamu.edu/caverlee/pubs/caverlee08alarge.pdf

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.

@inproceedings{narayanan2008robust, author = {Narayanan, Arvind and Shmatikov, Vitaly}, title = {Robust De-anonymization of Large Sparse Datasets}, booktitle = {Proc. of the 29th IEEE Symposium on Security and Privacy}, publisher = {IEEE Computer Society}, year = {2008}, pages = {111--125}, url = {http://www.cs.utexas.edu/~shmat/shmat_oak08netflix.pdf}, doi = {10.1109/SP.2008.33}, keywords = {anonymization, datamining, dataset, netflix, privacy, recommender, toread}, 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.} }

%0 = inproceedings %A = Narayanan, Arvind and Shmatikov, Vitaly %B = Proc. of the 29th IEEE Symposium on Security and Privacy %D = 2008 %I = IEEE Computer Society %T = Robust De-anonymization of Large Sparse Datasets %U = http://www.cs.utexas.edu/~shmat/shmat_oak08netflix.pdf

@inproceedings{1458098, author = {Song, Yang and Zhang, Lu and Giles, C. Lee}, title = {A sparse gaussian processes classification framework for fast tag suggestions}, booktitle = {CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge mining}, publisher = {ACM}, address = {New York, NY, USA}, year = {2008}, pages = {93--102}, url = {http://portal.acm.org/citation.cfm?id=1458098}, doi = {http://doi.acm.org/10.1145/1458082.1458098}, isbn = {978-1-59593-991-3}, keywords = {bibsonomy, bookmarking, classification, dataset, ml, recommender, social, tag, tagging, taggingsurvey, toread} }

%0 = inproceedings %A = Song, Yang and Zhang, Lu and Giles, C. Lee %B = CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge mining %C = New York, NY, USA %D = 2008 %I = ACM %T = A sparse gaussian processes classification framework for fast tag suggestions %U = http://portal.acm.org/citation.cfm?id=1458098

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.

@inproceedings{HaHe06, author = {Hassan-Montero, Y. and Herrero-Solana, V.}, title = {Improving Tag-Clouds as Visual Information Retrieval Interfaces}, booktitle = {InScit2006: International Conference on Multidisciplinary Information Sciences and Technologies}, year = {2006}, url = {http://nosolousabilidad.com/hassan/improving_tagclouds.pdf}, keywords = {clouds, dataset, del.icio.us, information, tag, tagging, taggingsurvey, toread, visual}, 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.} }

%0 = inproceedings %A = Hassan-Montero, Y. and Herrero-Solana, V. %B = InScit2006: International Conference on Multidisciplinary Information Sciences and Technologies %D = 2006 %T = Improving Tag-Clouds as Visual Information Retrieval Interfaces %U = http://nosolousabilidad.com/hassan/improving_tagclouds.pdf

@inproceedings{liu2006web, author = {Liu, Vinci and Curran, James R.}, title = {Web Text Corpus for Natural Language Processing.}, booktitle = {EACL}, publisher = {The Association for Computer Linguistics}, year = {2006}, url = {http://dblp.uni-trier.de/db/conf/eacl/eacl2006.html#LiuC06}, isbn = {1-932432-59-0}, keywords = {corpus, dataset, web, synonym_detection, nlp} }

%0 = inproceedings %A = Liu, Vinci and Curran, James R. %B = EACL %D = 2006 %I = The Association for Computer Linguistics %T = Web Text Corpus for Natural Language Processing. %U = http://dblp.uni-trier.de/db/conf/eacl/eacl2006.html#LiuC06

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.

@misc{narayanan-2006, author = {Narayanan, Arvind and Shmatikov, Vitaly}, title = {How To Break Anonymity of the Netflix Prize Dataset}, year = {2006}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cs/0610105}, keywords = {Preis, anonymity, dataset, netflix, prize, recommender}, 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.} }

%0 = misc %A = Narayanan, Arvind and Shmatikov, Vitaly %D = 2006 %T = How To Break Anonymity of the Netflix Prize Dataset %U = http://www.citebase.org/abstract?id=oai:arXiv.org:cs/0610105

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.

@article{McRae:2005:Behav-Res-Methods:16629288, author = {McRae, K and Cree, G S and Seidenberg, M S and McNorgan, C}, title = {Semantic feature production norms for a large set of living and nonliving things}, journal = {Behav Res Methods}, year = {2005}, volume = {37}, number = {4}, pages = {547-559}, url = {http://www.ncbi.nlm.nih.gov/pubmed/16629288}, keywords = {dataset, grounding, ol, ontology, relation, semantic, toread}, 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.} }

%0 = article %A = McRae, K and Cree, G S and Seidenberg, M S and McNorgan, C %D = 2005 %T = Semantic feature production norms for a large set of living and nonliving things %U = http://www.ncbi.nlm.nih.gov/pubmed/16629288

@misc{Newman+Hettich+Blake+Merz:1998, author = {Newman, C.L. Blake D.J. and Merz, C.J.}, title = {UCI Repository of machine learning databases}, year = {1998}, url = {http://www.ics.uci.edu/$mlearn/MLRepository.html}, keywords = {learning, data, dataset, dm, mining, machine, ml, uci} }

%0 = misc %A = Newman, C.L. Blake D.J. and Merz, C.J. %D = 1998 %T = UCI Repository of machine learning databases %U = http://www.ics.uci.edu/$mlearn/MLRepository.html