{"id":"https://openalex.org/W4415378698","doi":"https://doi.org/10.5753/sbbd.2025.247075","title":"Agente Aut\u00f4nomo Guiado por LLM para Extra\u00e7\u00e3o de Not\u00edcias","display_name":"Agente Aut\u00f4nomo Guiado por LLM para Extra\u00e7\u00e3o de Not\u00edcias","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4415378698","doi":"https://doi.org/10.5753/sbbd.2025.247075"},"language":null,"primary_location":{"id":"doi:10.5753/sbbd.2025.247075","is_oa":true,"landing_page_url":"https://doi.org/10.5753/sbbd.2025.247075","pdf_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/37244/37027","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XL Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/37244/37027","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120077045","display_name":"Jo\u00e3o V. C. Neres de Sousa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142721","display_name":"Hospital Universit\u00e1rio da Universidade de S\u00e3o Paulo","ror":"https://ror.org/0406jsq08","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I17974374","https://openalex.org/I4210142721"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o V. C. Neres de Sousa","raw_affiliation_strings":["Universidade de S\u00e3o Paulo (USP)"],"raw_orcid":"https://orcid.org/0009-0006-7885-9992","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo (USP)","institution_ids":["https://openalex.org/I4210142721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120077046","display_name":"Lucas M. Mingardo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146143","display_name":"Funda\u00e7\u00e3o Estadual de Prote\u00e7\u00e3o Ambiental Henrique Luiz Roessler","ror":"https://ror.org/057tp6a49","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210146143"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas M. Mingardo","raw_affiliation_strings":["Fundac\u00e3o Sistema Estadual de An\u00e1lise de Dados (Seade)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundac\u00e3o Sistema Estadual de An\u00e1lise de Dados (Seade)","institution_ids":["https://openalex.org/I4210146143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Carlos E. T. Freire","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146143","display_name":"Funda\u00e7\u00e3o Estadual de Prote\u00e7\u00e3o Ambiental Henrique Luiz Roessler","ror":"https://ror.org/057tp6a49","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210146143"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Carlos E. T. Freire","raw_affiliation_strings":["Fundac\u00e3o Sistema Estadual de An\u00e1lise de Dados (Seade)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundac\u00e3o Sistema Estadual de An\u00e1lise de Dados (Seade)","institution_ids":["https://openalex.org/I4210146143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014783020","display_name":"Agma J. M. Traina","orcid":"https://orcid.org/0000-0003-4929-7258"},"institutions":[{"id":"https://openalex.org/I4210142721","display_name":"Hospital Universit\u00e1rio da Universidade de S\u00e3o Paulo","ror":"https://ror.org/0406jsq08","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I17974374","https://openalex.org/I4210142721"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Agma J. M. Traina","raw_affiliation_strings":["Universidade de S\u00e3o Paulo (USP)"],"raw_orcid":"https://orcid.org/0000-0003-4929-7258","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo (USP)","institution_ids":["https://openalex.org/I4210142721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020611078","display_name":"Caetano Traina","orcid":"https://orcid.org/0000-0002-6625-6047"},"institutions":[{"id":"https://openalex.org/I4210142721","display_name":"Hospital Universit\u00e1rio da Universidade de S\u00e3o Paulo","ror":"https://ror.org/0406jsq08","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I17974374","https://openalex.org/I4210142721"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Caetano T. Junior","raw_affiliation_strings":["Universidade de S\u00e3o Paulo (USP)"],"raw_orcid":"https://orcid.org/0000-0002-6625-6047","affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo (USP)","institution_ids":["https://openalex.org/I4210142721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.36389468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8996999859809875,"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":0.8996999859809875,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.8406999707221985,"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/recall","display_name":"Recall","score":0.38839998841285706},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.31220000982284546},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.28459998965263367},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2630000114440918},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25200000405311584}],"concepts":[{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37290000915527344},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.36660000681877136},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.31709998846054077},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.2653999924659729},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C530479602","wikidata":"https://www.wikidata.org/wiki/Q1344","display_name":"Opera","level":2,"score":0.24740000069141388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5753/sbbd.2025.247075","is_oa":true,"landing_page_url":"https://doi.org/10.5753/sbbd.2025.247075","pdf_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/37244/37027","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XL Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5753/sbbd.2025.247075","is_oa":true,"landing_page_url":"https://doi.org/10.5753/sbbd.2025.247075","pdf_url":"https://sol.sbc.org.br/index.php/sbbd/article/download/37244/37027","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XL Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415378698.pdf","grobid_xml":"https://content.openalex.org/works/W4415378698.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4200146754","https://openalex.org/W4389166082","https://openalex.org/W4400111459","https://openalex.org/W4404782707"],"related_works":[],"abstract_inverted_index":{"A":[0],"manuten\u00e7\u00e3o":[1],"de":[2,31,66,70,90],"scrapers":[3],"com":[4,22,56,95],"seletores":[5],"fixos":[6],"\u00e9":[7],"onerosa,":[8],"pois":[9],"pequenas":[10],"mudan\u00e7as":[11],"nas":[12],"p\u00e1ginas":[13],"os":[14],"invalidam.":[15],"Este":[16],"artigo":[17],"prop\u00f5e":[18],"um":[19],"agente":[20,40],"aut\u00f4nomo":[21],"Large":[23],"Language":[24],"Model":[25],"(LLM)":[26],"e":[27,60,68],"prompts":[28],"din\u00e2micos,":[29,87],"capaz":[30],"extrair":[32],"not\u00edcias":[33],"sem":[34],"conhecimento":[35],"pr\u00e9vio":[36],"do":[37,75],"HTML.":[38],"O":[39,78],"opera":[41],"em":[42,85,92],"ciclos":[43],"observar\u2013planejar\u2013agir,":[44],"nos":[45],"quais":[46],"o":[47,73],"GPT-4":[48],"decide":[49],"a\u00e7\u00f5es":[50],"(rolagem,":[51],"clique,":[52],"extra\u00e7\u00e3o).":[53],"Em":[54],"testes":[55],"4.898URLs":[57],"da":[58],"Seade":[59],"12":[61],"portais":[62],"in\u00e9ditos,":[63],"obteve-se":[64],"91%":[65],"recall":[67],"95%":[69],"precision,":[71],"igualando":[72],"desempenho":[74],"scraper":[76],"legado.":[77],"sistema":[79],"manteve":[80],"qualidade":[81],"superior":[82],"a":[83],"90%":[84],"DOMs":[86],"viabilizando":[88],"monitoramento":[89],"m\u00eddia":[91],"larga":[93],"escala":[94],"m\u00ednima":[96],"interven\u00e7\u00e3o":[97],"humana.":[98]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-21T00:00:00"}
