{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T14:09:16Z","timestamp":1778681356682,"version":"3.51.4"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/legalcode"}],"funder":[{"name":"Medical Research Council","award":["MR\/L01078X\/1"],"award-info":[{"award-number":["MR\/L01078X\/1"]}]},{"name":"Medical Research Council","award":["MR\/N015665\/1"],"award-info":[{"award-number":["MR\/N015665\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2018,10,1]]},"DOI":"10.1109\/tkde.2017.2781721","type":"journal-article","created":{"date-parts":[[2018,2,23]],"date-time":"2018-02-23T19:40:06Z","timestamp":1519414806000},"page":"1929-1942","source":"Crossref","is-referenced-by-count":10,"title":["Self-Tuned Descriptive Document Clustering Using a Predictive Network"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7293-8140","authenticated-orcid":false,"given":"Austin J.","family":"Brockmeier","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6315-3432","authenticated-orcid":false,"given":"Tingting","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4097-9191","authenticated-orcid":false,"given":"Sophia","family":"Ananiadou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0381-124X","authenticated-orcid":false,"given":"John Y.","family":"Goulermas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"1371","article-title":"Towards ultrahigh dimensional feature selection for big data","volume":"15","author":"tan","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2007.910281"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2011.01004.x"},{"key":"ref70","article-title":"Glmnet for matlab 2013","author":"qian","year":"2013"},{"key":"ref76","first-page":"440","article-title":"Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification","author":"blitzer","year":"2007","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref77","article-title":"UCI machine learning repository","author":"lichman","year":"2013"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"ref39","first-page":"206","article-title":"Full-subtopic retrieval with keyphrase-based search results clustering","author":"bernardini","year":"2009","journal-title":"Proc IEEE\/WIC\/ACM Int Joint Conf Web Intell and Intell Agent Technol"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218990"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1145\/290941.290956","article-title":"Web document clustering: A feasibility demonstration","author":"zamir","year":"1998","journal-title":"Proc Annu ACM SIGIR Conf Res Develop Inf Retrieval"},{"key":"ref78","article-title":"Improving methods for single-label text categorization","author":"cardoso-cachopo","year":"2007"},{"key":"ref79","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"2015","journal-title":"Proc 28th Int Conf Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345578"},{"key":"ref32","first-page":"1183","article-title":"Distributional word clusters vs. words for text categorization","volume":"3","author":"bekkerman","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/981574.981598"},{"key":"ref30","first-page":"22","article-title":"Word association norms, mutual information, and lexicography","volume":"16","author":"church","year":"1990","journal-title":"Comput Ling"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199708)48:8<694::AID-ASI3>3.0.CO;2-N"},{"key":"ref35","author":"breiman","year":"1984","journal-title":"Classification and Regression Trees"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009031"},{"key":"ref60","first-page":"1150","article-title":"Grouped orthogonal matching pursuit for variable selection and prediction","volume":"22","author":"swirszcz","year":"2009","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"ref61","first-page":"807","article-title":"Greedy sparsity-constrained optimization","volume":"14","author":"bahmani","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref63","first-page":"318","article-title":"Learning internal representations by error propagation","volume":"1","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/288627.288651"},{"key":"ref64","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","volume":"27","author":"baldi","year":"2012","journal-title":"JMLR Workshop on Unsupervised and Transfer Learning"},{"key":"ref27","first-page":"333","author":"hearst","year":"1999","journal-title":"The Use of Categories and Clusters for Organizing Retrieval Results"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref66","first-page":"267","article-title":"Information theory and an extension of the maximum likelihood principle","author":"akaike","year":"1973","journal-title":"Proc 2nd Int Symp Inf Theory"},{"key":"ref29","first-page":"412","article-title":"A comparative study on feature selection in text categorization","author":"yang","year":"1997","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS054"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01"},{"key":"ref69","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/133160.133214"},{"key":"ref1","author":"salton","year":"1971","journal-title":"The SMART Retrieval System&#x2013;Experiments in Automatic Document Processing"},{"key":"ref20","first-page":"371","article-title":"Keyword selection method for characterizing text document maps","author":"lagus","year":"1999","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/38.974518"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/72.846729"},{"key":"ref24","first-page":"76","article-title":"Reexamining the cluster hypothesis: Scatter\/gather on retrieval results","author":"hearst","year":"1996","journal-title":"Proc Annu ACM SIGIR Conf Res Develop Inf Retrieval"},{"key":"ref23","first-page":"1536","article-title":"Automatic labelling of topic models","author":"lau","year":"2011","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/160688.160706"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2014.6970174"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"ref51","first-page":"694","article-title":"Integrating document clustering and topic modeling","author":"xie","year":"2013","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref59","first-page":"1333","article-title":"Grafting: Fast, incremental feature selection by gradient descent in function space","volume":"3","author":"perkins","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2008.923858"},{"key":"ref57","first-page":"687","article-title":"Data visualization and feature selection: New algorithms for nongaussian data","volume":"12","author":"yang","year":"2000","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"ref55","first-page":"1531","article-title":"Fast binary feature selection with conditional mutual information","volume":"5","author":"fleuret","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref54","first-page":"284","article-title":"Toward optimal feature selection","author":"koller","year":"1996","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","first-page":"483","article-title":"Towards subjectifying text clustering","author":"dasgupta","year":"2010","journal-title":"Proc Annu ACM SIGIR Conf Res Develop Inf Retrieval"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2345378"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2310059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344136"},{"key":"ref14","article-title":"Descriptive clustering as a method for exploring text collections","author":"weiss","year":"2006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541884"},{"key":"ref82","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/978-3-662-44851-9_15","article-title":"Optimal thresholding of classifiers to maximize F1 measure","author":"lipton","year":"2014","journal-title":"Proc Eur Conf Mach Learn Knowl Discovery Databases"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23374"},{"key":"ref81","first-page":"849","article-title":"On spectral clustering: Analysis and an algorithm","volume":"14","author":"ng","year":"2002","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2005.845141"},{"key":"ref18","first-page":"490","article-title":"Automatic labeling of multinomial topic models","author":"mei","year":"2007","journal-title":"Proc ACM SIGKDD Int Conf Knowl Discov Data Mining"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1987.4309069"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(98)00039-3"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"ref4","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"guyon","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(97)00043-X"},{"key":"ref6","first-page":"82","article-title":"Feature selection via concave minimization and support vector machines","author":"bradley","year":"1998","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","first-page":"27","article-title":"Conditional likelihood maximisation: A unifying framework for information theoretic feature selection","volume":"13","author":"brown","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref8","first-page":"1519","article-title":"An interior-point method for large-scale l1-regularized logistic regression","volume":"8","author":"koh","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref7","first-page":"49","article-title":"1-norm support vector machines","volume":"16","author":"zhu","year":"2004","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2009.07.048"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2414658"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"5228","DOI":"10.1073\/pnas.0307752101","article-title":"Finding scientific topics","volume":"101","author":"griffiths","year":"2004","journal-title":"Proc Natl Acad Sci USA"},{"key":"ref48","year":"2010"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2124295.2124324"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312649"},{"key":"ref41","first-page":"359","article-title":"Lingo: Search results clustering algorithm based on singular value decomposition","author":"osi?ski","year":"2004","journal-title":"Proc Int IIS Intell Inf Process Web Mining Conf"},{"key":"ref44","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref43","first-page":"386","article-title":"A thematic analysis of the AIDS literature","author":"wilbur","year":"2001","journal-title":"Proc Pacific Symp Biocomputing"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/8458057\/08301532.pdf?arnumber=8301532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T08:08:10Z","timestamp":1693555690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8301532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,1]]},"references-count":83,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2017.2781721","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,1]]}}}