{"id":"https://openalex.org/W4412913283","doi":"https://doi.org/10.21814/lm.17.1.451","title":"Estrat\u00e9gias de Sele\u00e7\u00e3o Informada de Dados para Aprendizado com Dados Escassos e Desbalanceados","display_name":"Estrat\u00e9gias de Sele\u00e7\u00e3o Informada de Dados para Aprendizado com Dados Escassos e Desbalanceados","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4412913283","doi":"https://doi.org/10.21814/lm.17.1.451"},"language":"pt","primary_location":{"id":"doi:10.21814/lm.17.1.451","is_oa":true,"landing_page_url":"https://doi.org/10.21814/lm.17.1.451","pdf_url":"https://linguamatica.com/index.php/linguamatica/article/download/451/545","source":{"id":"https://openalex.org/S2737670976","display_name":"Linguam\u00e1tica","issn_l":"1647-0818","issn":["1647-0818"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310318491","host_organization_name":"University of Minho","host_organization_lineage":["https://openalex.org/P4310318491"],"host_organization_lineage_names":["University of Minho"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Linguam\u00e1tica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://linguamatica.com/index.php/linguamatica/article/download/451/545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058079727","display_name":"Alexandre Alcoforado","orcid":"https://orcid.org/0000-0003-3184-1534"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alexandre Alcoforado","raw_affiliation_strings":["Universidade de S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0000-0003-3184-1534","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058000339","display_name":"Lucas H. Okamura","orcid":"https://orcid.org/0000-0002-7198-6140"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Okamura","raw_affiliation_strings":["Universidade de S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0000-0002-7198-6140","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068900854","display_name":"Thomas Palmeira Ferraz","orcid":"https://orcid.org/0000-0002-5385-9164"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Ferraz","raw_affiliation_strings":["T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris"],"raw_orcid":"https://orcid.org/0000-0002-5385-9164","affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093796329","display_name":"Israel Campos Fama","orcid":"https://orcid.org/0000-0001-6325-4153"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Israel Campos Fama","raw_affiliation_strings":["Universidade de S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0000-0001-6325-4153","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093796331","display_name":"B\u00e1rbara Dias Bueno","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"B\u00e1rbara Dias Bueno","raw_affiliation_strings":["Universidade de S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0009-0004-7455-3342","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010227979","display_name":"Bruno Veloso","orcid":"https://orcid.org/0000-0001-7980-0972"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Bruno Miguel Veloso","raw_affiliation_strings":["Universidade do Porto, INESC-TEC"],"raw_orcid":"https://orcid.org/0000-0001-7980-0972","affiliations":[{"raw_affiliation_string":"Universidade do Porto, INESC-TEC","institution_ids":["https://openalex.org/I4210166615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069264027","display_name":"Anna Helena Reali Costa","orcid":"https://orcid.org/0000-0001-7309-4528"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Anna Helena Reali Costa","raw_affiliation_strings":["Universidade de S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0000-0001-7309-4528","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25490742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":"105","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.6682999730110168,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.6682999730110168,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/psychology","display_name":"Psychology","score":0.4132826626300812},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3601887822151184},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.339620977640152}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4132826626300812},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3601887822151184},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.339620977640152}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21814/lm.17.1.451","is_oa":true,"landing_page_url":"https://doi.org/10.21814/lm.17.1.451","pdf_url":"https://linguamatica.com/index.php/linguamatica/article/download/451/545","source":{"id":"https://openalex.org/S2737670976","display_name":"Linguam\u00e1tica","issn_l":"1647-0818","issn":["1647-0818"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310318491","host_organization_name":"University of Minho","host_organization_lineage":["https://openalex.org/P4310318491"],"host_organization_lineage_names":["University of Minho"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Linguam\u00e1tica","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05583849v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05583849","pdf_url":"https://hal.science/hal-05583849v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://linguamatica.com/index.php/linguamatica/pt/article/view/451","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:c55a223ad5d442479ee98f969b2bbb12","is_oa":true,"landing_page_url":"https://doaj.org/article/c55a223ad5d442479ee98f969b2bbb12","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Linguam\u00e1tica, Vol 17, Iss 1 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.21814/lm.17.1.451","is_oa":true,"landing_page_url":"https://doi.org/10.21814/lm.17.1.451","pdf_url":"https://linguamatica.com/index.php/linguamatica/article/download/451/545","source":{"id":"https://openalex.org/S2737670976","display_name":"Linguam\u00e1tica","issn_l":"1647-0818","issn":["1647-0818"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310318491","host_organization_name":"University of Minho","host_organization_lineage":["https://openalex.org/P4310318491"],"host_organization_lineage_names":["University of Minho"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Linguam\u00e1tica","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412913283.pdf","grobid_xml":"https://content.openalex.org/works/W4412913283.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2935759653","https://openalex.org/W3105167352","https://openalex.org/W54078636","https://openalex.org/W2954470139","https://openalex.org/W1501425562","https://openalex.org/W2902782467","https://openalex.org/W3084825885"],"abstract_inverted_index":{"A":[0],"obten\u00e7\u00e3o":[1],"de":[2,5,15,22,49,52,57,72,92,110,115,122],"dados":[3,28,53,66,93,132],"anotados":[4,30],"alta":[6],"qualidade":[7,61],"\u00e9":[8,80],"um":[9],"dos":[10,131,159],"principais":[11],"desafios":[12],"no":[13],"Processamento":[14],"Linguagem":[16],"Natural":[17],"(PLN),":[18],"especialmente":[19],"em":[20,90,152,174],"m\u00e9todos":[21,136,172],"aprendizado":[23],"supervisionado.":[24],"Em":[25],"cen\u00e1rios":[26,153],"onde":[27,95],"previamente":[29],"n\u00e3o":[31,78],"est\u00e3o":[32],"dispon\u00edveis,":[33],"solu\u00e7\u00f5es":[34],"comuns":[35],"como":[36],"o":[37,120,157],"crowdsourcing":[38],"e":[39,54,82,113,129,155,170,180],"a":[40,47,55,87,127,138,147,168],"abordagem":[41],"zero-shot":[42],"frequentemente":[43],"apresentam":[44],"limita\u00e7\u00f5es,":[45],"incluindo":[46],"necessidade":[48],"grandes":[50],"volumes":[51],"falta":[56],"garantias":[58],"quanto":[59],"\u00e0":[60],"das":[62],"anota\u00e7\u00f5es.":[63],"Tradicionalmente,":[64],"os":[65,135],"para":[67,118],"anota\u00e7\u00e3o":[68],"humana":[69],"s\u00e3o":[70,99],"selecionados":[71],"forma":[73],"aleat\u00f3ria,":[74],"uma":[75,108,165],"pr\u00e1tica":[76],"que":[77],"s\u00f3":[79],"custosa":[81],"ineficiente,":[83],"mas":[84],"tamb\u00e9m":[85],"suscet\u00edvel":[86],"vi\u00e9s,":[88],"particularmente":[89],"conjuntos":[91],"desbalanceados,":[94],"as":[96],"classes":[97],"minorit\u00e1rias":[98],"sub-representadas.":[100],"Para":[101],"enfrentar":[102],"esses":[103],"desafios,":[104],"este":[105],"trabalho":[106],"apresenta":[107],"arquitetura":[109],"sele\u00e7\u00e3o":[111,148],"autom\u00e1tica":[112],"informada":[114],"dados,":[116],"projetada":[117],"minimizar":[119],"volume":[121],"anota\u00e7\u00f5es":[123],"necess\u00e1rias":[124],"enquanto":[125],"maximiza":[126],"diversidade":[128],"representatividade":[130],"selecionados.":[133],"Entre":[134],"avaliados,":[137],"Busca":[139],"Sem\u00e2ntica":[140],"Reversa":[141],"(RSS)":[142],"se":[143],"destacou,":[144],"superando":[145],"consistentemente":[146],"por":[149],"amostragem":[150],"aleat\u00f3ria":[151],"desbalanceados":[154],"melhorando":[156],"desempenho":[158],"classificadores":[160],"treinados.":[161],"Al\u00e9m":[162],"disso,":[163],"realiza-se":[164],"compara\u00e7\u00e3o":[166],"entre":[167],"RSS":[169],"outros":[171],"baseados":[173],"agrupamento,":[175],"discutindo":[176],"seus":[177],"pontos":[178],"fortes":[179],"fracos.":[181]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
