{"id":"https://openalex.org/W4297102408","doi":"https://doi.org/10.1145/3539637.3557054","title":"An Auto-ML Approach Applied to Text Classification","display_name":"An Auto-ML Approach Applied to Text Classification","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4297102408","doi":"https://doi.org/10.1145/3539637.3557054"},"language":"en","primary_location":{"id":"doi:10.1145/3539637.3557054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539637.3557054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062797630","display_name":"Douglas Nunes de Oliveira","orcid":"https://orcid.org/0000-0002-0698-1845"},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Douglas Nunes de Oliveira","raw_affiliation_strings":["Department of Computer Science, Federal University of Lavras, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Lavras, Brazil","institution_ids":["https://openalex.org/I1315085146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028036865","display_name":"Luiz Henrique de Campos Merschmann","orcid":"https://orcid.org/0000-0002-9948-2673"},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luiz Henrique de Campos Merschmann","raw_affiliation_strings":["Department of Applied Computing, Federal University of Lavras, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Computing, Federal University of Lavras, Brazil","institution_ids":["https://openalex.org/I1315085146"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6937,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75453118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7379218339920044},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.7340508103370667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.672126829624176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6646008491516113},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.647165834903717},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.493838369846344},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47023504972457886},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4390731453895569},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40467172861099243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10255903005599976},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08824193477630615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379218339920044},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7340508103370667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.672126829624176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6646008491516113},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.647165834903717},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.493838369846344},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47023504972457886},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4390731453895569},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40467172861099243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10255903005599976},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08824193477630615},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539637.3557054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539637.3557054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G511133346","display_name":null,"funder_award_id":"406411/2021-2","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G5803995671","display_name":null,"funder_award_id":"APQ-02176-21","funder_id":"https://openalex.org/F4320322980","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais"}],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W60686164","https://openalex.org/W1576660662","https://openalex.org/W1647221522","https://openalex.org/W1792568252","https://openalex.org/W1992205670","https://openalex.org/W2014545475","https://openalex.org/W2021891520","https://openalex.org/W2060199218","https://openalex.org/W2102539288","https://openalex.org/W2112036188","https://openalex.org/W2154776925","https://openalex.org/W2177019876","https://openalex.org/W2208124221","https://openalex.org/W2215376118","https://openalex.org/W2309832917","https://openalex.org/W2471350540","https://openalex.org/W2475024326","https://openalex.org/W2475776616","https://openalex.org/W2531563875","https://openalex.org/W2554135467","https://openalex.org/W2604766410","https://openalex.org/W2732547613","https://openalex.org/W2792682186","https://openalex.org/W2909045715","https://openalex.org/W2963686598","https://openalex.org/W2997591727","https://openalex.org/W3128381090","https://openalex.org/W4211116959","https://openalex.org/W4389994700"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W2602382373","https://openalex.org/W3003615511","https://openalex.org/W3198113463","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W4285827128","https://openalex.org/W2787698406","https://openalex.org/W2963844355","https://openalex.org/W2390529043"],"abstract_inverted_index":{"Automated":[0],"Machine":[1,14],"Learning":[2,15],"(AutoML)":[3],"is":[4,50,199],"a":[5,32,37,43,70,143],"research":[6],"area":[7],"that":[8,118,196],"aims":[9],"to":[10,52,68,101,126,141,201],"help":[11],"humans":[12],"solve":[13],"(ML)":[16],"problems":[17],"by":[18,156],"automatically":[19],"discovering":[20],"good":[21,71,144],"model":[22,145],"pipelines":[23,98],"(algorithms":[24],"and":[25,139,169],"their":[26],"hyperparameters":[27],"for":[28,36,47,114,147],"every":[29],"stage":[30],"of":[31,88,97,183,206],"machine":[33],"learning":[34],"process)":[35],"given":[38],"dataset.":[39],"Since":[40],"we":[41,106,177],"have":[42],"combinatorial":[44],"optimization":[45],"problem":[46],"which":[48],"it":[49,158],"impossible":[51],"evaluate":[53,77,127,153],"all":[54,209],"possible":[55],"pipelines,":[56],"most":[57],"AutoML":[58,172],"systems":[59,75],"use":[60,178],"Evolutionary":[61],"Algorithm":[62],"(EA)":[63],"or":[64,202],"Bayesian":[65],"Optimization":[66,166],"(BO)":[67],"find":[69,142],"solution.":[72],"As":[73],"these":[74],"usually":[76],"the":[78,82,86,95,103,120,128,133,148,163,189],"pipelines\u2019":[79,129],"performance":[80],"using":[81],"k-fold":[83],"cross-validation":[84],"method,":[85],"chance":[87],"finding":[89],"an":[90,108],"overfitted":[91],"solution":[92],"increases":[93],"with":[94],"number":[96],"evaluated.":[99],"Therefore,":[100],"avoid":[102],"aforementioned":[104],"issue,":[105],"propose":[107],"Auto-ML":[109,112],"system,":[110],"named":[111],"System":[113],"Text":[115],"Classification":[116],"(ASTeC),":[117],"uses":[119],"Bootstrap":[121],"Bias":[122],"Corrected":[123],"CV":[124],"(BBC-CV)":[125],"performance.":[130],"More":[131],"specifically,":[132],"proposed":[134],"system":[135,198],"combines":[136],"EA,":[137],"BO,":[138],"BBC-CV":[140],"pipeline":[146],"text":[149],"classification":[150],"task.":[151],"We":[152],"our":[154,197],"proposal":[155],"comparing":[157],"against":[159],"two":[160],"state-of-the-art":[161],"systems,":[162],"Tree-based":[164],"Pipeline":[165],"Tool":[167],"(TPOT)":[168],"Google":[170],"Cloud":[171],"service.":[173],"To":[174],"do":[175],"so,":[176],"seven":[179],"public":[180],"datasets":[181],"composed":[182],"written":[184],"Brazilian":[185],"Portuguese":[186],"texts":[187],"from":[188],"sentiment":[190],"analysis":[191],"domain.":[192],"Statistical":[193],"tests":[194],"show":[195],"equivalent":[200],"better":[203],"than":[204],"both":[205],"them":[207],"in":[208],"evaluated":[210],"datasets.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}