{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:10:52Z","timestamp":1760710252469,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG041861"],"award-info":[{"award-number":["R01AG041861"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s42979-020-00148-5","type":"journal-article","created":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T11:04:54Z","timestamp":1589281494000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Web Similarity in Sets of Search Terms Using Database Queries"],"prefix":"10.1007","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7707-5970","authenticated-orcid":false,"given":"Andrew R.","family":"Cohen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul M. B.","family":"Vit\u00e1nyi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,12]]},"reference":[{"key":"148_CR1","doi-asserted-by":"crossref","unstructured":"Ahmeti AK et al. Age of onset of amyotrophic lateral sclerosis is modulated by a locus on 1p34.1. Neurobiol Aging. 2013;34:1 (357.e357\u2013357.e319).","DOI":"10.1016\/j.neurobiolaging.2012.07.017"},{"issue":"1","key":"148_CR2","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1063\/1.2008594","volume":"779","author":"JP Bagrow","year":"2005","unstructured":"Bagrow JP, Ben-Avraham D. On the Google-fame of scientists and other populations. AIP Conf Proc. 2005;779(1):81\u20139.","journal-title":"AIP Conf Proc."},{"issue":"4","key":"148_CR3","doi-asserted-by":"publisher","first-page":"1407","DOI":"10.1109\/18.681318","volume":"44","author":"CH Bennett","year":"1998","unstructured":"Bennett CH, G\u00e1cs P, Li M, Vit\u00e1nyi PMB, Zurek W. Information distance. IEEE Trans Inform Theory. 1998;44(4):1407\u201323.","journal-title":"IEEE Trans Inform Theory"},{"issue":"3","key":"148_CR4","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/TKDE.2007.48","volume":"19","author":"RL Cilibrasi","year":"2007","unstructured":"Cilibrasi RL, Vit\u00e1nyi PMB. The Google similarity distance. IEEE Trans Knowl Data Eng. 2007;19(3):370\u201383.","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"148_CR5","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1145\/1046456.1046460","volume":"6","author":"P Cimiano","year":"2004","unstructured":"Cimiano P, Staab S. Learning by Googling. SIGKDD Explor. 2004;6(2):24\u201333.","journal-title":"SIGKDD Explor"},{"issue":"6","key":"148_CR6","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1093\/aje\/kwh059","volume":"159","author":"H Chen","year":"2004","unstructured":"Chen H, et al. Obesity and the risk of Parkinson\u2019s disease. Am J Epidemiol. 2004;159(6):547\u201355.","journal-title":"Am J Epidemiol."},{"issue":"8","key":"148_CR7","doi-asserted-by":"publisher","first-page":"1386","DOI":"10.1109\/TPAMI.2008.162","volume":"31","author":"AR Cohen","year":"2009","unstructured":"Cohen AR, Bjornsson C, Temple S, Banker G, Roysam B. Automatic summarization of changes in biological image sequences using algorithmic information theory. IEEE Trans Pattern Anal Mach Intell. 2009;31(8):1386\u2013403.","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"issue":"3","key":"148_CR8","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1038\/nmeth.1424","volume":"7","author":"AR Cohen","year":"2010","unstructured":"Cohen AR, Gomes F, Roysam B, Cayouette M. Computational prediction of neural progenitor cell fates. Nat. Methods. 2010;7(3):213\u20138.","journal-title":"Nat. Methods"},{"issue":"8","key":"148_CR9","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1109\/TPAMI.2014.2375175","volume":"37","author":"AR Cohen","year":"2015","unstructured":"Cohen AR, Vit\u00e1nyi PMB. Normalized compression distance of multisets with applications. IEEE Trans Pattern Anal Mach Intell. 2015;37(8):1602\u201314.","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"key":"148_CR10","unstructured":"G\u00e1cs P. On the symmetry of algorithmic information. Sov Math Dokl. 1947;15:1477\u201380 (correction ibid. 1974;15(1974):1480)."},{"issue":"42","key":"148_CR11","doi-asserted-by":"publisher","first-page":"11254","DOI":"10.1523\/JNEUROSCI.3272-07.2007","volume":"27","author":"HS Huang","year":"2007","unstructured":"Huang HS, et al. Prefrontal dysfunction in schizophrenia involves mixed-lineage leukemia 1-regulated histone methylation at GABAergic gene promoters. J Neurosci. 2007;27(42):11254\u201362.","journal-title":"J Neurosci."},{"issue":"5","key":"148_CR12","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1089\/jop.2015.0163","volume":"32","author":"R Joshi","year":"2016","unstructured":"Joshi R, et al. Automated measurement of cobblestone morphology for characterizing stem cell derived retinal pigment epithelial cell cultures. J Ocular Pharmacol Ther. 2016;32(5):331\u20139.","journal-title":"J Ocular Pharmacol Ther."},{"key":"148_CR13","doi-asserted-by":"publisher","first-page":"e117","DOI":"10.1038\/tp.2012.45","volume":"2","author":"MI Kamboh","year":"2012","unstructured":"Kamboh MI, et al. Genome-wide association study of Alzheimer\u2019s disease. Transl Psychiatry Nat. 2012;2:e117.","journal-title":"Transl Psychiatry Nat"},{"issue":"3","key":"148_CR14","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1162\/089120103322711604","volume":"29","author":"F Keller","year":"2003","unstructured":"Keller F, Lapata M. Using the web to obtain frequencies for unseen bigrams. Comput Linguist. 2003;29(3):459\u201384.","journal-title":"Comput Linguist"},{"issue":"1","key":"148_CR15","first-page":"1","volume":"1","author":"AN Kolmogorov","year":"1965","unstructured":"Kolmogorov AN. Three approaches to the quantitative definition of information. Probl Inform Transm. 1965;1(1):1\u20137.","journal-title":"Probl Inform Transm"},{"key":"148_CR16","unstructured":"Kraft LG. A device for quantizing, grouping, and coding amplitude modulated pulses. MS thesis, EE Department, Massachusetts Institute of Technology, Cambridge."},{"key":"148_CR17","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1037\/0033-295X.104.2.211","volume":"104","author":"T Landauer","year":"1997","unstructured":"Landauer T, Dumais S. A solution to Plato\u2019s problem: the latent semantic analysis theory of acquisition, induction and representation of knowledge. Psychol Rev. 1997;104:211\u201340.","journal-title":"Psychol Rev."},{"key":"148_CR18","unstructured":"LeCun Y, Cortes C, Burges CJC. The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"148_CR19","first-page":"206","volume":"10","author":"LA Levin","year":"1974","unstructured":"Levin LA. Laws of information conservation (nongrowth) and aspects of the foundation of probability theory. Probl Inform Transm. 1974;10:206\u201310.","journal-title":"Probl Inform Transm."},{"key":"148_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-49820-1","volume-title":"An introduction to Kolmogorov complexity and its applications","author":"M Li","year":"2008","unstructured":"Li M, Vit\u00e1nyi PMB. An introduction to Kolmogorov complexity and its applications. 3rd ed. New York: Springer; 2008.","edition":"3"},{"key":"148_CR21","doi-asserted-by":"crossref","unstructured":"Long C, Zhu X, Li M, Ma B. Information shared by many objects. Proceedings of the 17th ACM conference on information and knowledge management, pp. 1213\u20131220 (2008).","DOI":"10.1145\/1458082.1458242"},{"issue":"24","key":"148_CR22","doi-asserted-by":"publisher","first-page":"2585","DOI":"10.1056\/NEJMoa0708698","volume":"358","author":"JM Maris","year":"2008","unstructured":"Maris JM. Chromosome 6p22 locus associated with clinically aggressive neuroblastoma. N Engl J Med. 2008;358(24):2585\u201393.","journal-title":"N Engl J Med"},{"issue":"4","key":"148_CR23","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1109\/TIT.1956.1056818","volume":"2","author":"B McMillan","year":"1956","unstructured":"McMillan B. Two inequalities implied by unique decipherability. IEEE Trans Inform Theory. 1956;2(4):115\u20136.","journal-title":"IEEE Trans Inform Theory"},{"key":"148_CR24","doi-asserted-by":"crossref","unstructured":"Michel J-B, Shen YK, Aiden AP, Veres A, Gray MK, Team TGB et al. Quantitative analysis of culture using millions of digitized books. Science 2011;331:176\u201382.","DOI":"10.1126\/science.1199644"},{"key":"148_CR25","unstructured":"Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. ICLR workshop. 2013. arXiv:1301.3781."},{"key":"148_CR26","unstructured":"Ng AY, Jordan M, Weiss Y. On spectral clustering: analysis and an algorithm. Adv Neural Inform Process Syst. 2002;14:849."},{"issue":"4","key":"148_CR27","doi-asserted-by":"publisher","first-page":"e1000916","DOI":"10.1371\/journal.pgen.1000916","volume":"6","author":"A Scherag","year":"2010","unstructured":"Scherag A, et al. Two new loci for body-weight regulation identified in a joint analysis of genome-wide association studies for early-onset extreme obesity in French and German Study Groups. PLoS Genet. 2010;6(4):e1000916.","journal-title":"PLoS Genet."},{"issue":"7510","key":"148_CR28","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1038\/nature13595","volume":"511","author":"Schizophrenia Working Group of the Psychiatric Genomics Consortium","year":"2014","unstructured":"Schizophrenia Working Group of the Psychiatric Genomics Consortium. Biological insights from 108 schizophrenia-associated genetic loci. Nature. 2014;511(7510):421\u20137.","journal-title":"Nature"},{"key":"148_CR29","doi-asserted-by":"crossref","unstructured":"Shannon CE. The mathematical theory of communication. Bell Syst Tech J. 1948;27:379\u2013423 (623\u2013656).","DOI":"10.1002\/j.1538-7305.1948.tb00917.x"},{"issue":"1","key":"148_CR30","doi-asserted-by":"publisher","first-page":"e29632","DOI":"10.1371\/journal.pone.0029632","volume":"7","author":"FCM Sill\u00e9","year":"2012","unstructured":"Sill\u00e9 FCM, et al. Post-GWAS functional characterization of susceptibility variants for chronic lymphocytic leukemia. PLoS One. 2012;7(1):e29632.","journal-title":"PLoS One"},{"issue":"4","key":"148_CR31","first-page":"287","volume":"2","author":"AI Soto-Ortolaza","year":"2013","unstructured":"Soto-Ortolaza AI, et al. GWAS risk factors in Parkinson\u2019s disease: LRRK2 coding variation and genetic interaction with PARK16. Am J Neurodegener Dis. 2013;2(4):287\u201399.","journal-title":"Am J Neurodegener Dis."},{"key":"148_CR32","doi-asserted-by":"crossref","unstructured":"Tan P-N, Kumar V, Srivastava J. Selecting the right interestingness measure for associating patterns. Proceedings of the ACM-SIGKDD conference knowledge discovery and data mining, 2002; pp. 491\u2013502.","DOI":"10.1145\/775047.775053"},{"key":"148_CR33","volume-title":"Frequency estimates for statistical word similarity measures, 37\/162 in human language theory conference (HLT\/NAACL 2003)","author":"E Terra","year":"2003","unstructured":"Terra E, Clarke CLA. Frequency estimates for statistical word similarity measures, 37\/162 in human language theory conference (HLT\/NAACL 2003). Alberta: Edmonton; 2003."},{"issue":"4","key":"148_CR34","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1109\/TIT.2011.2110130","volume":"57","author":"PMB Vit\u00e1nyi","year":"2011","unstructured":"Vit\u00e1nyi PMB. Information distance in multiples. IEEE Trans Inform Theory. 2011;57(4):2451\u20136.","journal-title":"IEEE Trans Inform Theory"},{"issue":"8","key":"148_CR35","doi-asserted-by":"publisher","first-page":"4725","DOI":"10.1109\/TIT.2017.2686883","volume":"63","author":"PMB Vit\u00e1nyi","year":"2017","unstructured":"Vit\u00e1nyi PMB. Exact expression for information distance. IEEE Trans Inform Theory. 2017;63(8):4725\u20138.","journal-title":"IEEE Trans Inform Theory."},{"key":"148_CR36","unstructured":"Witten IH, Frank E. Data mining: practical machine learning tools and techniques. 2005."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00148-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-020-00148-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00148-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T23:41:50Z","timestamp":1620776510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-020-00148-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["148"],"URL":"https:\/\/doi.org\/10.1007\/s42979-020-00148-5","relation":{},"ISSN":["2662-995X","2661-8907"],"issn-type":[{"type":"print","value":"2662-995X"},{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2020,5]]},"assertion":[{"value":"19 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"161"}}