@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

@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