{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T07:47:38Z","timestamp":1772264858459,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T00:00:00Z","timestamp":1602892800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T00:00:00Z","timestamp":1602892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","award":["001"],"award-info":[{"award-number":["001"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Evolving Systems"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s12530-020-09357-y","type":"journal-article","created":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T18:02:33Z","timestamp":1602957753000},"page":"997-1013","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A comparative study of feature selection methods for binary text streams classification"],"prefix":"10.1007","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9485-0334","authenticated-orcid":false,"given":"Matheus Bernardelli","family":"de Moraes","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6520-9740","authenticated-orcid":false,"given":"Andre Leon Sampaio","family":"Gradvohl","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,17]]},"reference":[{"issue":"November 2017","key":"9357_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jnca.2017.12.001","volume":"103","author":"MD de Assun\u00e7\u00e3o","year":"2018","unstructured":"de Assun\u00e7\u00e3o MD, da Silva Veith A, Buyya R (2018) Distributed data stream processing and edge computing: a survey on resource elasticity and future directions. J Netw Comput Appl 103(November 2017):1\u201317. https:\/\/doi.org\/10.1016\/j.jnca.2017.12.001","journal-title":"J Netw Comput Appl"},{"key":"9357_CR2","unstructured":"Asuncion A, Newman D (2007) UCI machine learning repository. http:\/\/www.ics.uci.edu\/~mlearn\/MLRepository.html"},{"key":"9357_CR3","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-26532-2_3","volume-title":"Neural information processing","author":"JP Barddal","year":"2015","unstructured":"Barddal JP, Gomes HM, Enembreck F (2015) Analyzing the impact of feature drifts in streaming learning. Neural information processing. Springer, Berlin, pp 21\u201328. https:\/\/doi.org\/10.1007\/978-3-319-26532-2_3"},{"key":"9357_CR4","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.jss.2016.07.005","volume":"127","author":"JP Barddal","year":"2017","unstructured":"Barddal JP, Gomes HM, Enembreck F, Pfahringer B (2017) A survey on feature drift adaptation: definition, benchmark, challenges and future directions. J Syst Softw 127:278\u2013294. https:\/\/doi.org\/10.1016\/j.jss.2016.07.005","journal-title":"J Syst Softw"},{"key":"9357_CR5","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1016\/j.ejor.2018.07.009","volume":"272","author":"P Baumann","year":"2019","unstructured":"Baumann P, Hochbaum DS, Yang YT (2019) A comparative study of the leading machine learning techniques and two new optimization algorithms. Eur J Oper Res 272:1041\u20131057. https:\/\/doi.org\/10.1016\/j.ejor.2018.07.009","journal-title":"Eur J Oper Res"},{"key":"9357_CR6","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-642-52307-6_8","volume-title":"Multiple hypothesenpr\u00fcfung \/ multiple hypotheses testing","author":"B Bergmann","year":"1988","unstructured":"Bergmann B, Hommel G (1988) Improvements of general multiple test procedures for redundant systems of hypotheses. In: Bauer P, Hommel G, Sonnemann E (eds) Multiple hypothesenpr\u00fcfung \/ multiple hypotheses testing. Springer, Berlin, pp 100\u2013115"},{"key":"9357_CR7","first-page":"1601","volume":"11","author":"A Bifet","year":"2010","unstructured":"Bifet A, Holmes G, Kirkby R, Pfahringer B (2010) MOA: massive online analysis. J Mach Learn Res 11:1601\u20131604","journal-title":"J Mach Learn Res"},{"key":"9357_CR8","unstructured":"Bifet A, Kirkby R (2009) Data stream mining a practical approach"},{"key":"9357_CR9","doi-asserted-by":"publisher","unstructured":"Brenes DJ, Gayo-Avello D, P\u00e9rez-Gonz\u00e1lez K (2009) Survey and evaluation of query intent detection methods. In: Proceedings of the 2009 workshop on web search click data, ACM, New York, NY, USA, WSCD \u201909, pp 1\u20137.https:\/\/doi.org\/10.1145\/1507509.1507510","DOI":"10.1145\/1507509.1507510"},{"key":"9357_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20192-9","volume-title":"Statistics for high-dimensional data. springer series in Statistics","author":"P B\u00fchlmann","year":"2011","unstructured":"B\u00fchlmann P, van de Geer S (2011) Statistics for high-dimensional data. springer series in Statistics. Springer, Berlin. https:\/\/doi.org\/10.1007\/978-3-642-20192-9"},{"key":"9357_CR11","doi-asserted-by":"publisher","unstructured":"Carvalho VR, Cohen WW (2006) Single-pass online learning: Performance, voting schemes and online feature selection. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, ACM, New York, NY, USA, KDD \u201906, pp 548\u2013553. https:\/\/doi.org\/10.1145\/1150402.1150466","DOI":"10.1145\/1150402.1150466"},{"issue":"6","key":"9357_CR12","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1080\/03610928008827904","volume":"9","author":"JM Davenport","year":"1980","unstructured":"Davenport JM (1980) Approximations of the critical region of the friedman statistic. Communi Stat Theory Methods 9(6):571\u2013595. https:\/\/doi.org\/10.1080\/03610928008827904","journal-title":"Communi Stat Theory Methods"},{"key":"9357_CR13","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/1-84628-103-2_1","volume-title":"Applications and innovations in intelligent systems XII","author":"SJ Delany","year":"2005","unstructured":"Delany SJ, Cunningham P, Tsymbal A, Coyle L (2005) A case-based technique for tracking concept drift in spam filtering. In: Macintosh A, Ellis R, Allen T (eds) Applications and innovations in intelligent systems XII. Springer, London, pp 3\u201316"},{"key":"9357_CR14","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Lear Res 7:1\u201330","journal-title":"J Mach Lear Res"},{"issue":"1","key":"9357_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.swevo.2011.02.002","volume":"1","author":"J Derrac","year":"2011","unstructured":"Derrac J, Garc\u00eda S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evol Comput 1(1):3\u201318. https:\/\/doi.org\/10.1016\/j.swevo.2011.02.002","journal-title":"Swarm Evol Comput"},{"issue":"4","key":"9357_CR16","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","volume":"52","author":"DL Donoho","year":"2006","unstructured":"Donoho DL (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289\u20131306. https:\/\/doi.org\/10.1109\/TIT.2006.871582","journal-title":"IEEE Trans Inf Theory"},{"issue":"1","key":"9357_CR17","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/TSC.2015.2439695","volume":"9","author":"S Fong","year":"2016","unstructured":"Fong S, Wong R, Vasilakos AV, Member S (2016) Accelerated PSO swarm search feature selection for data stream mining big data. IEEE Trans Serv Comput 9(1):33\u201345. https:\/\/doi.org\/10.1109\/TSC.2015.2439695","journal-title":"IEEE Trans Serv Comput"},{"issue":"3","key":"9357_CR18","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/s10994-012-5320-9","volume":"90","author":"J Gama","year":"2013","unstructured":"Gama J, Sebasti\u00e3o R, Rodrigues PP (2013) On evaluating stream learning algorithms. Mach Learn 90(3):317\u2013346","journal-title":"Mach Learn"},{"issue":"4","key":"9357_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2523813","volume":"46","author":"J Gama","year":"2014","unstructured":"Gama J, \u017dliobait\u0117 I, Bifet A, Pechenizkiy M, Bouchachia A (2014) A survey on concept drift adaptation. ACM Comput Surv 46(4):1\u201337. https:\/\/doi.org\/10.1145\/2523813","journal-title":"ACM Comput Surv"},{"issue":"December 2008","key":"9357_CR20","first-page":"2677","volume":"9","author":"S Garc\u00eda","year":"2008","unstructured":"Garc\u00eda S, Herrera F (2008) An extension on \u201cstatistical comparisons of classifiers over multiple data sets\u201d for all pairwise comparisons. J Mach Learn Res 9(December 2008):2677\u20132694","journal-title":"J Mach Learn Res"},{"issue":"1","key":"9357_CR21","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1109\/TNNLS.2013.2271915","volume":"25","author":"JB Gomes","year":"2014","unstructured":"Gomes JB, Gaber MM, Sousa PAC, Menasalvas E (2014) Mining recurring concepts in a dynamic feature space. IEEE Trans Neural Netw Learn Syst 25(1):95\u2013110. https:\/\/doi.org\/10.1109\/TNNLS.2013.2271915","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"2","key":"9357_CR22","doi-asserted-by":"publisher","first-page":"174","DOI":"10.4304\/jetwi.6.2.174-179","volume":"6","author":"ALS Gradvohl","year":"2014","unstructured":"Gradvohl ALS, Senger H, Arantes L, Sens P (2014) Comparing distributed online stream processing systems considering fault tolerance issues. J Emerg Technol Web Intell 6(2):174\u2013179. https:\/\/doi.org\/10.4304\/jetwi.6.2.174-179","journal-title":"J Emerg Technol Web Intell"},{"issue":"3","key":"9357_CR23","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/j.aca.2011.07.027","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3(3):1157\u20131182. https:\/\/doi.org\/10.1016\/j.aca.2011.07.027","journal-title":"J Mach Learn Res"},{"key":"9357_CR24","volume-title":"Data mining concepts and techniques","author":"J Han","year":"2011","unstructured":"Han J, Kamber M, Pei J (2011) Data mining concepts and techniques, vol 3. Morgan Kaufmann, Burlington"},{"issue":"9","key":"9357_CR25","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263\u20131284","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9357_CR26","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.1016\/j.procs.2016.05.508","volume":"80","author":"D Jankowski","year":"2016","unstructured":"Jankowski D, Jackowski K, Cyganek B (2016) Learning decision trees from data streams with concept drift. Proced Comput Sci 80:1682\u20131691. https:\/\/doi.org\/10.1016\/j.procs.2016.05.508","journal-title":"Proced Comput Sci"},{"issue":"2","key":"9357_CR27","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s10844-008-0053-8","volume":"32","author":"I Katakis","year":"2009","unstructured":"Katakis I, Tsoumakas G, Banos E, Bassiliades N, Vlahavas I (2009) An adaptive personalized news dissemination system. J Intell Inf Syst 32(2):191\u2013212. https:\/\/doi.org\/10.1007\/s10844-008-0053-8","journal-title":"J Intell Inf Syst"},{"key":"9357_CR28","first-page":"763","volume-title":"Anais da 18 ECAI: European conference on artificial intelligence","author":"I Katakis","year":"2008","unstructured":"Katakis I, Tsoumakas G, Vlahavas I (2008) An ensemble of classifiers for coping with recurring contexts in data streams. Anais da 18 ECAI: European conference on artificial intelligence. IOS Press, Amsterdam, pp 763\u2013764"},{"issue":"3","key":"9357_CR29","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/s10115-009-0206-2","volume":"22","author":"I Katakis","year":"2010","unstructured":"Katakis I, Tsoumakas G, Vlahavas I (2010) Tracking recurring contexts using ensemble classifiers: an application to email filtering. Knowl Inf Syst 22(3):371\u2013391. https:\/\/doi.org\/10.1007\/s10115-009-0206-2","journal-title":"Knowl Inf Syst"},{"key":"9357_CR30","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/11573036_32","volume-title":"Advances in informatics","author":"I Katakis","year":"2005","unstructured":"Katakis I, Tsoumakas G, Vlahavas I (2005) On the utility of incremental feature selection for the classification of textual data streams. In: Bozanis P, Houstis EN (eds) Advances in informatics. Springer, Berlin, pp 338\u2013348"},{"key":"9357_CR31","first-page":"2755","volume":"8","author":"JZ Kolter","year":"2007","unstructured":"Kolter JZ, Maloof MA (2007) Dynamic weighted majority: an ensemble method for drifting concepts. J Mach Learn Rese 8:2755\u20132790","journal-title":"J Mach Learn Rese"},{"issue":"45","key":"9357_CR32","doi-asserted-by":"publisher","first-page":"1970","DOI":"10.21105\/joss.01970","volume":"5","author":"MB Moraes","year":"2020","unstructured":"Moraes MB, Gradvohl ALS (2020). MOAFS: A Massive Online Analysis library for feature selection in data streams. J Open Source Software 5(45):1970. https:\/\/doi.org\/10.21105\/joss.01970","journal-title":"J Open Source Software"},{"key":"9357_CR33","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/11790853_9","volume-title":"Advances in data mining. Applications in medicine, web mining, marketing, image and signal mining","author":"JR M\u00e9ndez","year":"2006","unstructured":"M\u00e9ndez JR, Fdez-Riverola F, D\u00edaz F, Iglesias EL, Corchado JM (2006) A comparative performance study of feature selection methods for the anti-spam filtering domain. In: Perner P (ed) Advances in data mining. Applications in medicine, web mining, marketing, image and signal mining. Springer, Berlin, pp 106\u2013120"},{"key":"9357_CR34","unstructured":"OpenML (2019) https:\/\/www.openml.org"},{"key":"9357_CR35","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-1-4612-4380-9_2","volume-title":"On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling","author":"K Pearson","year":"1992","unstructured":"Pearson K (1992) On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Springer, New York, pp 11\u201328. https:\/\/doi.org\/10.1007\/978-1-4612-4380-9_2"},{"issue":"1","key":"9357_CR36","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1023\/A:1022643204877","volume":"1","author":"JR Quinlan","year":"1986","unstructured":"Quinlan JR (1986) Induction of decision trees. Mach Learn 1(1):81\u2013106. https:\/\/doi.org\/10.1023\/A:1022643204877","journal-title":"Mach Learn"},{"key":"9357_CR37","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2017.01.078","volume":"239","author":"S Ram\u00edrez-Gallego","year":"2017","unstructured":"Ram\u00edrez-Gallego S, Krawczyk B, Garc\u00eda S, Wo\u017aniak M, Herrera F (2017) A survey on data preprocessing for data stream mining: current status and future directions. Neurocomputing 239:39\u201357. https:\/\/doi.org\/10.1016\/j.neucom.2017.01.078","journal-title":"Neurocomputing"},{"issue":"1","key":"9357_CR38","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.inffus.2006.11.002","volume":"9","author":"A Tsymbal","year":"2008","unstructured":"Tsymbal A, Pechenizkiy M, Cunningham P, Puuronen S (2008) Dynamic integration of classifiers for handling concept drift. Inf Fusion 9(1):56\u201368. https:\/\/doi.org\/10.1016\/j.inffus.2006.11.002","journal-title":"Inf Fusion"},{"issue":"3","key":"9357_CR39","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.websem.2011.05.003","volume":"9","author":"S Wang","year":"2011","unstructured":"Wang S, Schlobach S, Klein M (2011) Concept drift and how to identify it. J Web Semant 9(3):247\u2013265. https:\/\/doi.org\/10.1016\/j.websem.2011.05.003","journal-title":"J Web Semant"},{"issue":"3","key":"9357_CR40","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1109\/TKDE.2013.32","volume":"26","author":"J Wang","year":"2014","unstructured":"Wang J, Zhao P, Hoi SC, Jin R (2014) Online feature selection and its applications. IEEE Trans Knowl Data Eng 26(3):698\u2013710. https:\/\/doi.org\/10.1109\/TKDE.2013.32","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9357_CR41","doi-asserted-by":"publisher","unstructured":"Wang L, Shen H (2016) Improved data streams classification with fast unsupervised feature selection. In: 17th international conference on parallel and distributed computing, applications and technologies (PDCAT), IEEE, Guangzhou, China, pp 221\u2013226. https:\/\/doi.org\/10.1109\/PDCAT.2016.056","DOI":"10.1109\/PDCAT.2016.056"},{"issue":"5","key":"9357_CR42","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1109\/TPAMI.2012.197","volume":"35","author":"X Wu","year":"2013","unstructured":"Wu X, Yu K, Ding W, Wang H, Zhu X, Member S (2013) Online feature selection with streaming features. IEEE Trans Pattern Anal Mach Intell 35(5):1178\u20131192. https:\/\/doi.org\/10.1109\/TPAMI.2012.197","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9357_CR43","unstructured":"Yang Y, Pedersen JO (1997) A comparative study on feature selection in text categorization. In: Proceedings of the fourteenth international conference on machine learning. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, ICML \u201997, pp 412\u2013420"},{"key":"9357_CR44","unstructured":"Yu L, Liu H (2003) Feature selection for high-dimensional data: a fast correlation-based filter solution. International conference on machine learning (ICML) pp 1\u20138"},{"issue":"2","key":"9357_CR45","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/s10115-018-1236-4","volume":"60","author":"L Yue","year":"2019","unstructured":"Yue L, Chen W, Li X, Zuo W, Yin M (2019) A survey of sentiment analysis in social media. Knowl Inf Syst 60(2):617\u2013663. https:\/\/doi.org\/10.1007\/s10115-018-1236-4","journal-title":"Knowl Inf Syst"},{"key":"9357_CR46","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.patcog.2018.08.009","volume":"86","author":"P Zhou","year":"2019","unstructured":"Zhou P, Hu X, Li P, Wu X (2019) OFS-density: a novel online streaming feature selection method. Pattern Recogn 86:48\u201361. https:\/\/doi.org\/10.1016\/j.patcog.2018.08.009","journal-title":"Pattern Recogn"}],"container-title":["Evolving Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-020-09357-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12530-020-09357-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-020-09357-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T18:37:49Z","timestamp":1635619069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12530-020-09357-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,17]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["9357"],"URL":"https:\/\/doi.org\/10.1007\/s12530-020-09357-y","relation":{},"ISSN":["1868-6478","1868-6486"],"issn-type":[{"value":"1868-6478","type":"print"},{"value":"1868-6486","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,17]]},"assertion":[{"value":"12 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}