{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:07:36Z","timestamp":1782947256797,"version":"3.54.5"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T00:00:00Z","timestamp":1500940800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1186\/s40537-017-0083-6","type":"journal-article","created":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T11:42:39Z","timestamp":1500982959000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":90,"title":["Improved sqrt-cosine similarity measurement"],"prefix":"10.1186","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1800-1696","authenticated-orcid":false,"given":"Sahar","family":"Sohangir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingding","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,7,25]]},"reference":[{"key":"83_CR1","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1613\/jair.2934","volume":"37","author":"C Potts","year":"2010","unstructured":"Potts C. From frequency to meaning: vector space models of semantics. J Artif Intell Res. 2010;37:141\u201388.","journal-title":"J Artif Intell Res"},{"key":"83_CR2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Schutze H. Introduction to information retrieval. New York: Cambridge; 2008. p. 279\u201388."},{"issue":"1","key":"83_CR3","doi-asserted-by":"crossref","first-page":"30","DOI":"10.4018\/IJKDB.2017010103","volume":"7","author":"P Tiwari","year":"2017","unstructured":"Tiwari P, Mishra BK, Kumar S, Kumar V. Implementation of n-gram methodology for rotten tomatoes review dataset sentiment analysis. Int J Knowl Discov Bioinform. 2017;7(1):30\u201341.","journal-title":"Int J Knowl Discov Bioinform"},{"issue":"4","key":"83_CR4","first-page":"748","volume":"52","author":"D Dubin","year":"2004","unstructured":"Dubin D. The most influential paper gerard salton never wrote. Libr Trends. 2004;52(4):748\u201364.","journal-title":"Libr Trends"},{"key":"83_CR5","doi-asserted-by":"crossref","unstructured":"Aggarwal CC, Hinneburg A, Keim DA. On the surprising behavior of distance metrics in high dimensional space. In: international conference on database theory. Springer; 2001. p. 420\u201334.","DOI":"10.1007\/3-540-44503-X_27"},{"key":"83_CR6","volume-title":"Taxicab geometry: an adventure in non-euclidean geometry","author":"EF Krause","year":"1987","unstructured":"Krause EF. Taxicab geometry: an adventure in non-euclidean geometry. New York: Dover Publications; 1987."},{"issue":"13","key":"83_CR7","first-page":"0975","volume":"68","author":"WH Gomaa","year":"2013","unstructured":"Gomaa WH, Fahmy AA. A survey of text similarity approaches. Int J Comput Appl. 2013;68(13):0975\u20138887.","journal-title":"Int J Comput Appl"},{"issue":"2","key":"83_CR8","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1111\/j.1467-9868.2008.00700.x","volume":"71","author":"H Rue","year":"2009","unstructured":"Rue H, Martino S, Chopin N. Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations. J R Stat Soc Series B Stat Methodol. 2009;71(2):319\u201392.","journal-title":"J R Stat Soc Series B Stat Methodol"},{"issue":"1","key":"83_CR9","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback S, Leibler RA. On information and sufficiency. Ann. Math. Statist. 1951;22(1):70\u201386.","journal-title":"Ann. Math. Statist."},{"issue":"4","key":"83_CR10","first-page":"300","volume":"1","author":"SH Cha","year":"2007","unstructured":"Cha SH. Comprehensive survey on distance\/similarity measures between probability density functions. Int. J. Math. Models Methods Appl. Sci. 2007;1(4):300\u20137.","journal-title":"Int. J. Math. Models Methods Appl. Sci."},{"key":"83_CR11","unstructured":"Schoenharl TW, Madey G. Evaluation of measurement techniques for the validation of agent-based simulations against streaming data. In: Bubak M, van Albada GD, Dongarra J, Sloot PMA, editors. Computational science\u2014ICCS 2008. ICCS 2008. Lecture notes in computer science, vol. 5103. Berlin, Heidelberg: Springer; 1998."},{"issue":"1","key":"83_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-015-0036-x","volume":"3","author":"S Kumar","year":"2016","unstructured":"Kumar S, Toshniwal D. Analysis of hourly road accident counts using hierarchical clustering and cophenetic correlation coefficient. J Big Data. 2016;3(1):1\u201311.","journal-title":"J Big Data"},{"issue":"1","key":"83_CR13","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s40537-016-0044-5","volume":"3","author":"S Kumar","year":"2016","unstructured":"Kumar S, Toshniwal D. A novel framework to analyze raod accident time series data. J Big Data. 2016;3(1):8.","journal-title":"J Big Data"},{"issue":"6","key":"83_CR14","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1007\/BF01033886","volume":"14","author":"MG Michie","year":"1982","unstructured":"Michie MG. Use of the bray-curtis similarity measure in cluster analysis of foraminiferal data. Math Geol. 1982;14(6):661\u20137.","journal-title":"Math Geol"},{"key":"83_CR15","doi-asserted-by":"crossref","unstructured":"Gonzalez CG, Bonventil W, Rodrigues AV. Density of closed balls in real-valued and autometrized boolean spaces for clustering applications. In: Brazilian symposium artificial intelligence. 2008. p. 8\u201322.","DOI":"10.1007\/978-3-540-88190-2_7"},{"issue":"2","key":"83_CR16","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1002\/j.1538-7305.1950.tb00463.x","volume":"29","author":"RW Hamming","year":"1950","unstructured":"Hamming RW. Error detecting and error correcting codes. Bell Syst Tech. 1950;29(2):147\u201360.","journal-title":"Bell Syst Tech"},{"key":"83_CR17","doi-asserted-by":"crossref","unstructured":"Aslam JA, Frost M. An information-theoretic measure for document similarity. In: Proceedings of the 26th annual international ACM SIGIR conference on research and development in informaion retrieval. 2003. p. 449\u201350.","DOI":"10.1145\/860435.860545"},{"key":"83_CR18","unstructured":"Lin D. An information-theoretic definition of similarity. In: Shavlik JW, editor. Proceedings of the fifteenth international conference on machine learning. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.; 1998. p. 296\u2013304."},{"issue":"9","key":"83_CR19","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1109\/TKDE.2008.50","volume":"20","author":"H Chim","year":"2008","unstructured":"Chim H, Deng X. Efficient phrase-based document similarity for clustering. IEEE Trans Knowl Data Eng. 2008;20(9):1217\u201329.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"83_CR20","volume-title":"Pattern classification","author":"RO Duda","year":"2012","unstructured":"Duda RO, Hart PE, Stork DG. Pattern classification. Hoboken: John Wiley & Sons; 2012."},{"key":"83_CR21","doi-asserted-by":"crossref","first-page":"2997","DOI":"10.1364\/AO.29.002997","volume":"29","author":"BVKV Kumar","year":"1990","unstructured":"Kumar BVKV, Hassebrook L. Performance measures for correlation filters. Appl Optics. 1990;29:2997\u20133006.","journal-title":"Appl Optics"},{"key":"83_CR22","unstructured":"Tanimoto TT. IBM internal Report; 1957."},{"key":"83_CR23","first-page":"241","volume":"37","author":"P Jaccard","year":"1901","unstructured":"Jaccard P. Distribution of the alpine flora in the dranses basin and some neighbouring regions. Bull Soc vaudoise Sci Nat. 1901;37:241\u201372.","journal-title":"Bull Soc vaudoise Sci Nat"},{"key":"83_CR24","first-page":"297","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice LR. Measures of the amount of ecologic association between species, ecology. Appl Optics. 1945;26:297\u2013302.","journal-title":"Appl Optics"},{"key":"83_CR25","first-page":"7","volume":"51","author":"V Monev","year":"2004","unstructured":"Monev V. Introduction to similarity searching in chemistry. MATCH Commun. Math. Comput. Chem. 2004;51:7\u201338.","journal-title":"MATCH Commun. Math. Comput. Chem."},{"key":"83_CR26","first-page":"65","volume":"3","author":"M Morisita","year":"1959","unstructured":"Morisita M. Measuring of interspecific association and similarity between communities. Series E Biol. 1959;3:65\u201380.","journal-title":"Series E Biol"},{"issue":"3","key":"83_CR27","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"L Dice","year":"1945","unstructured":"Dice L. Measures of the amount of ecologic association between species. Ecology. 1945;26(3):297\u2013302.","journal-title":"Ecology"},{"key":"83_CR28","volume-title":"Dictionary of distance","author":"M-M Deza","year":"2006","unstructured":"Deza M-M, Deza E. Dictionary of distance. Amsterdam: Elsevier; 2006."},{"issue":"3","key":"83_CR29","first-page":"491","volume":"18","author":"G Sidorov","year":"2014","unstructured":"Sidorov G, Gelbukh A, Gomez-Adorno H, Pinto D. Soft similarity and soft cosine measure:similarity of features in vector space model. Computacion y Sistemas. 2014;18(3):491\u2013504.","journal-title":"Computacion y Sistemas"},{"issue":"12","key":"83_CR30","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1016\/j.ins.2010.02.021","volume":"180","author":"J Dhondt","year":"2010","unstructured":"Dhondt J, Vertommen J, Vertommen PA, Cattrysse D, Duflou JR. Pairwise-adaptive dissimilarity measure for document clustering. Inf Sci. 2010;180(12):2341\u201358.","journal-title":"Inf. Sci."},{"key":"83_CR31","doi-asserted-by":"crossref","unstructured":"Zhu S, Liu L, Wang Y. Information retrieval using hellinger distance and sqrt-cos similarity. In: International Conference on computer science and education (ICCSE 2012); 2012. p. 14\u201317.","DOI":"10.1109\/ICCSE.2012.6295217"},{"issue":"11","key":"83_CR32","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia M, Xin RS, Wendell P, Das T, Armbrust M, Dave A, Meng X, Rosen J, Venkataraman S, Franklin MJ, et al. Apache Spark: a unified engine for big data processing. Commun ACM. 2016;59(11):56\u201365.","journal-title":"Commun ACM"},{"issue":"4","key":"83_CR33","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1109\/TBDATA.2016.2622719","volume":"2","author":"AJ Wellings","year":"2016","unstructured":"Wellings AJ, Gray I, Fernndez Garca N, Basanta-Val P, Audsley NC. Architecting time-critical big-data systems. IEEE Trans Big Data. 2016;2(4):310\u201324.","journal-title":"IEEE Trans Big Data"},{"key":"83_CR34","first-page":"22","volume":"52","author":"AJ Wellings","year":"2015","unstructured":"Wellings AJ, Audsley NC, Basanta-Val P, Fernndez Garca N. Improving the predictability of distributed stream processors. Commun ACM. 2015;52:22\u201336.","journal-title":"Commun ACM"},{"key":"83_CR35","doi-asserted-by":"crossref","unstructured":"Wang D, Sohangir S, Li T. Update summarization using semi-supervised learning based on hellinger distance. In: Proceedings of the 24th ACM international on conference on information and knowledge management. 2015. p. 1907\u201310.","DOI":"10.1145\/2806416.2806628"},{"key":"83_CR36","doi-asserted-by":"crossref","unstructured":"Han S, Boley D, Gini M, Gross R, Hastings K, Karypis G, Kumar V, Mobasher B, Moore J. Webace: a web agent for document categorization and exploration. In: proceedings of the second international conference on autonomous agents; 1998. p. 408\u201315.","DOI":"10.1145\/280765.280872"},{"key":"83_CR37","unstructured":"Cardoso-Cachopo A. Improving methods for single-label text categorization. PdD Thesis, Instituto Superior Tecnico, Universidade Tecnica de Lisboa; 2007."},{"key":"83_CR38","doi-asserted-by":"crossref","unstructured":"Beyer K, Goldstein J, Ramakrishnan R, Shaft U. When Is \u201cNearest Neighbor\u201d Meaningful?. In: Beeri C, Buneman P. editors. Database Theory\u2014ICDT\u201999. ICDT 1999. Lecture notes in computer science, vol. 1540. Berlin, Heidelberg: Springer; 1999. p. 217\u201335.","DOI":"10.1007\/3-540-49257-7_15"},{"key":"83_CR39","volume-title":"Machine Learning","author":"TM Mitchell","year":"1997","unstructured":"Mitchell TM. Machine Learning. Boston, MA: McGraw-Hill; 1997."},{"key":"83_CR40","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77242-4","volume-title":"Support vector machine","author":"I Steinwart","year":"2008","unstructured":"Steinwart I, Christmann A. Support vector machine. New York: Springer; 2008."},{"key":"83_CR41","unstructured":"Macqueen J. Some methods forclassification and analysis of multivariate observations. In: Berkeley Symposium on mathematical statistics and probability; 2009. p. 281\u201397."},{"key":"83_CR42","doi-asserted-by":"crossref","unstructured":"Shi J, Malik J. Self inducing relational distance and its application to image segmentation. In: proceedings of the 5th European conference on computer vision (ECCV\u201998); 1998. p. 528\u201343.","DOI":"10.1007\/BFb0055688"},{"issue":"7","key":"83_CR43","first-page":"41","volume":"13","author":"D Napoleon","year":"2011","unstructured":"Napoleon D, Pavalakodi S. A new method for dimensionality reduction using k-means clustering algorithm for high dimensional data set. Int J Comput Appl. 2011;13(7):41\u20136.","journal-title":"Int J Comput Appl"},{"key":"83_CR44","doi-asserted-by":"crossref","DOI":"10.1201\/9780429292859","volume-title":"Data mining with R","author":"L Torgo","year":"2011","unstructured":"Torgo L. Data mining with R. Boca Raton: CRC Press; 2011."},{"key":"83_CR45","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning","author":"T Hastie","year":"2009","unstructured":"Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. New York: Springer; 2009."},{"key":"83_CR46","volume-title":"Advanced data mining techniques","author":"DL Olson","year":"2008","unstructured":"Olson DL, Delen D. Advanced data mining techniques. New York: Springer; 2008."},{"key":"83_CR47","doi-asserted-by":"crossref","unstructured":"Wang D, Li T, Ding C. Weighted feature subset non-negative matrix factorization and its applications to document understanding. In: IEEE international conference on data mining; 2010.","DOI":"10.1109\/ICDM.2010.47"},{"issue":"3","key":"83_CR48","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1145\/1993077.1993078","volume":"5","author":"D Wang","year":"2011","unstructured":"Wang D, Zhu S, Li T. Integrating document clustering and multidocument summarization. ACM Trans Knowl Discov Data. 2011;5(3):14.","journal-title":"ACM Trans Knowl Discov Data"},{"key":"83_CR49","volume-title":"Intermediate statistical methods and applications: a computer package approach","author":"ML Berenson","year":"1983","unstructured":"Berenson ML, Levine DM, Goldstein M. Intermediate statistical methods and applications: a computer package approach. New Jersey: Prentice-Hall; 1983."},{"key":"83_CR50","doi-asserted-by":"crossref","unstructured":"Tukey JW. Comparing individual means in the analysis of variance. In: international biometric society; 2009. 5(2).","DOI":"10.2307\/3001913"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-017-0083-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-017-0083-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-017-0083-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T17:49:14Z","timestamp":1750787354000},"score":1,"resource":{"primary":{"URL":"http:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-017-0083-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,25]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["83"],"URL":"https:\/\/doi.org\/10.1186\/s40537-017-0083-6","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,25]]},"article-number":"25"}}