{"id":"https://openalex.org/W4417017966","doi":"https://doi.org/10.1093/jigpal/jzaf044","title":"Comparative analysis of data sampling techniques for legal text classification in real-world scenarios","display_name":"Comparative analysis of data sampling techniques for legal text classification in real-world scenarios","publication_year":2025,"publication_date":"2025-05-16","ids":{"openalex":"https://openalex.org/W4417017966","doi":"https://doi.org/10.1093/jigpal/jzaf044"},"language":"en","primary_location":{"id":"doi:10.1093/jigpal/jzaf044","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jigpal/jzaf044","pdf_url":null,"source":{"id":"https://openalex.org/S2734381524","display_name":"Logic Journal of IGPL","issn_l":"1367-0751","issn":["1367-0751","1368-9894"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Logic Journal of the IGPL","raw_type":"journal-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/A5075884794","display_name":"Daniela L. Freire","orcid":"https://orcid.org/0000-0002-5363-3608"},"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":true,"raw_author_name":"Daniela L Freire","raw_affiliation_strings":["University of Sao Paulo , Sao Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"University of Sao Paulo , Sao Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leandro O da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I88273585","display_name":"Universidade Federal de S\u00e3o Paulo","ror":"https://ror.org/02k5swt12","country_code":"BR","type":"education","lineage":["https://openalex.org/I88273585"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leandro O da Silva","raw_affiliation_strings":["Federal University of Sao Paulo , S\u00e3o Jos\u00e9 dos Campos, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Sao Paulo , S\u00e3o Jos\u00e9 dos Campos, Brazil","institution_ids":["https://openalex.org/I88273585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085731066","display_name":"M\u00e1rcio de Souza Dias","orcid":"https://orcid.org/0000-0003-1116-6965"},"institutions":[{"id":"https://openalex.org/I88273585","display_name":"Universidade Federal de S\u00e3o Paulo","ror":"https://ror.org/02k5swt12","country_code":"BR","type":"education","lineage":["https://openalex.org/I88273585"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"M\u00e1rcio de S  Dias","raw_affiliation_strings":["Federal University of Catal\u00e3o , Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Catal\u00e3o , Brazil","institution_ids":["https://openalex.org/I88273585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002033728","display_name":"Alex Marino Gon\u00e7alves de Almeida","orcid":"https://orcid.org/0000-0002-6805-3753"},"institutions":[{"id":"https://openalex.org/I4210144790","display_name":"Ourofino Sa\u00fade Animal (Brazil)","ror":"https://ror.org/0435yq060","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210144790"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alex M G de Almeida","raw_affiliation_strings":["Ourinhos College of Technology , Brazil"],"affiliations":[{"raw_affiliation_string":"Ourinhos College of Technology , Brazil","institution_ids":["https://openalex.org/I4210144790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004221623","display_name":"Adriano R\u00edvolli","orcid":"https://orcid.org/0000-0001-6445-3007"},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Adriano Rivolli","raw_affiliation_strings":["Federal Technological University of Paran\u00e1 , Brazil"],"affiliations":[{"raw_affiliation_string":"Federal Technological University of Paran\u00e1 , Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013466267","display_name":"Fab\u00edola S. F. Pereira","orcid":"https://orcid.org/0000-0003-2914-1803"},"institutions":[{"id":"https://openalex.org/I80850581","display_name":"Universidade Federal de Uberl\u00e2ndia","ror":"https://ror.org/04x3wvr31","country_code":"BR","type":"education","lineage":["https://openalex.org/I80850581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fab\u00edola S F Pereira","raw_affiliation_strings":["Federal University of Uberl\u00e2ndia , Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Uberl\u00e2ndia , Brazil","institution_ids":["https://openalex.org/I80850581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078892245","display_name":"Giliard A. de Godoi","orcid":"https://orcid.org/0000-0002-1715-0852"},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Giliard A de Godoi","raw_affiliation_strings":["Federal Technological University of Paran\u00e1 , Brazil"],"affiliations":[{"raw_affiliation_string":"Federal Technological University of Paran\u00e1 , Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090283789","display_name":"M\u00e1rcio P. Basgalupp","orcid":"https://orcid.org/0000-0002-2005-1249"},"institutions":[{"id":"https://openalex.org/I88273585","display_name":"Universidade Federal de S\u00e3o Paulo","ror":"https://ror.org/02k5swt12","country_code":"BR","type":"education","lineage":["https://openalex.org/I88273585"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"M\u00e1rcio P Basgalupp","raw_affiliation_strings":["Federal University of Sao Paulo , S\u00e3o Jos\u00e9 dos Campos, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Sao Paulo , S\u00e3o Jos\u00e9 dos Campos, Brazil","institution_ids":["https://openalex.org/I88273585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079499583","display_name":"Andr\u00e9 C. P. L. F. de Carvalho","orcid":"https://orcid.org/0000-0002-4765-6459"},"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"]},{"id":"https://openalex.org/I4210086099","display_name":"Microsoft (Brazil)","ror":"https://ror.org/00hc2mf91","country_code":"BR","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210086099"]},{"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":"Andre C P L F de Carvalho","raw_affiliation_strings":["University of Sao Paulo, Sao Paulo , Brazil"],"affiliations":[{"raw_affiliation_string":"University of Sao Paulo, Sao Paulo , Brazil","institution_ids":["https://openalex.org/I4210086099","https://openalex.org/I4210142721","https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5075884794"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":{"value":4151,"currency":"USD","value_usd":4151},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19717163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.392300009727478,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.392300009727478,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.10939999669790268,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.08160000294446945,"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/class","display_name":"Class (philosophy)","score":0.49720001220703125},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3743000030517578},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.35530000925064087},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.2930999994277954},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29120001196861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775000095367432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5139999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138999819755554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C522695570","wikidata":"https://www.wikidata.org/wiki/Q6517578","display_name":"Legal research","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/jigpal/jzaf044","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jigpal/jzaf044","pdf_url":null,"source":{"id":"https://openalex.org/S2734381524","display_name":"Logic Journal of IGPL","issn_l":"1367-0751","issn":["1367-0751","1368-9894"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Logic Journal of the IGPL","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1978394996","https://openalex.org/W1993220166","https://openalex.org/W2107138773","https://openalex.org/W2116702209","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2562319768","https://openalex.org/W2953926847","https://openalex.org/W4214519989"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"article":[2],"investigates":[3],"the":[4,16],"use":[5],"of":[6],"machine":[7],"learning":[8,66],"(ML)":[9],"for":[10,49],"classifying":[11],"legal":[12,28,87,108],"texts,":[13],"focusing":[14],"on":[15],"challenges":[17],"posed":[18],"by":[19],"imbalanced":[20],"class":[21],"distributions":[22,45],"in":[23,98,107],"datasets.":[24],"In":[25],"Brazil,":[26],"where":[27],"processes":[29],"are":[30,75],"numerous":[31],"and":[32,39,72,81],"complex,":[33],"ML":[34],"could":[35],"improve":[36,82],"judicial":[37],"efficiency":[38],"decision-making":[40],"speed.":[41],"However,":[42],"skewed":[43],"data":[44,79,88],"make":[46],"it":[47],"difficult":[48],"standard":[50],"algorithms":[51],"to":[52,77],"perform":[53],"well":[54],"across":[55],"all":[56],"classes,":[57],"often":[58],"neglecting":[59],"minority":[60],"categories.":[61],"To":[62],"address":[63],"this,":[64],"imbalance":[65],"strategies":[67],"such":[68],"as":[69],"oversampling,":[70],"undersampling,":[71],"hybrid":[73],"methods":[74],"applied":[76],"balance":[78],"sets":[80],"classification":[83],"accuracy.":[84],"Using":[85],"real":[86],"from":[89],"S\u00e3o":[90],"Paulo,":[91],"this":[92],"study":[93],"evaluates":[94],"these":[95],"techniques\u2019":[96],"effectiveness":[97],"binary":[99],"classification,":[100],"providing":[101],"valuable":[102],"insights":[103],"into":[104],"their":[105],"applicability":[106],"settings.":[109]},"counts_by_year":[],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-12-05T00:00:00"}
