{"id":"https://openalex.org/W4412939643","doi":"https://doi.org/10.1109/access.2025.3595423","title":"Investigating the Relationship Between Text Vectorization Cosine Similarity and Classification Performance","display_name":"Investigating the Relationship Between Text Vectorization Cosine Similarity and Classification Performance","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412939643","doi":"https://doi.org/10.1109/access.2025.3595423"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3595423","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3595423","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3595423","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000010910","display_name":"Fernando Rezende Zagatti","orcid":"https://orcid.org/0000-0002-7083-5789"},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fernando Rezende Zagatti","raw_affiliation_strings":["Department of Computing, Federal University of São Carlos, São Carlos, São Paulo, Brazil","Department of Computing, Federal University of São Carlos, São Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-7083-5789","affiliations":[{"raw_affiliation_string":"Department of Computing, Federal University of São Carlos, São Carlos, São Paulo, Brazil","institution_ids":["https://openalex.org/I177909021"]},{"raw_affiliation_string":"Department of Computing, Federal University of São Carlos, São Carlos, SP, Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004525547","display_name":"Gilson Shimizu","orcid":"https://orcid.org/0000-0003-3711-5592"},"institutions":[{"id":"https://openalex.org/I4210142333","display_name":"Centro de Tecnologia da Informa\u00e7\u00e3o Renato Archer","ror":"https://ror.org/044nfga98","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210142333","https://openalex.org/I4210151455"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gilson Yuuji Shimizu","raw_affiliation_strings":["DIMEC, Center for Information Technology Renato Archer, Campinas, São Paulo, Brazil","DIMEC, Center for Information Technology Renato Archer, Campinas, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-3711-5592","affiliations":[{"raw_affiliation_string":"DIMEC, Center for Information Technology Renato Archer, Campinas, São Paulo, Brazil","institution_ids":["https://openalex.org/I4210142333"]},{"raw_affiliation_string":"DIMEC, Center for Information Technology Renato Archer, Campinas, SP, Brazil","institution_ids":["https://openalex.org/I4210142333"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081840975","display_name":"Daniel Lucr\u00e9dio","orcid":"https://orcid.org/0000-0002-1360-4036"},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniel Lucr\u00e9dio","raw_affiliation_strings":["Department of Computing, Federal University of São Carlos, São Carlos, São Paulo, Brazil","Department of Computing, Federal University of São Carlos, São Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-1360-4036","affiliations":[{"raw_affiliation_string":"Department of Computing, Federal University of São Carlos, São Carlos, São Paulo, Brazil","institution_ids":["https://openalex.org/I177909021"]},{"raw_affiliation_string":"Department of Computing, Federal University of São Carlos, São Carlos, SP, Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087505547","display_name":"Helena de Medeiros Caseli","orcid":"https://orcid.org/0000-0003-3996-8599"},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Helena de Medeiros Caseli","raw_affiliation_strings":["Department of Computing, Federal University of São Carlos, São Carlos, São Paulo, Brazil","Department of Computing, Federal University of São Carlos, São Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-3996-8599","affiliations":[{"raw_affiliation_string":"Department of Computing, Federal University of São Carlos, São Carlos, São Paulo, Brazil","institution_ids":["https://openalex.org/I177909021"]},{"raw_affiliation_string":"Department of Computing, Federal University of São Carlos, São Carlos, SP, Brazil","institution_ids":["https://openalex.org/I177909021"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87828279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"137348","last_page":"137363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9218000173568726,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9218000173568726,"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":0.7632818222045898},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.7480394840240479},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7119570970535278},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6419727206230164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4798983335494995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40175682306289673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38513073325157166},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.09241673350334167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632818222045898},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.7480394840240479},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7119570970535278},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6419727206230164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4798983335494995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40175682306289673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38513073325157166},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.09241673350334167},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3595423","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3595423","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:30e6947c6f774cc7b2df1b620ca726f5","is_oa":true,"landing_page_url":"https://doaj.org/article/30e6947c6f774cc7b2df1b620ca726f5","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":"IEEE Access, Vol 13, Pp 137348-137363 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3595423","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3595423","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2130187411","https://openalex.org/W2493916176","https://openalex.org/W2907776084","https://openalex.org/W2920189126","https://openalex.org/W2945830544","https://openalex.org/W2969250152","https://openalex.org/W2970053908","https://openalex.org/W2996765369","https://openalex.org/W2997276102","https://openalex.org/W3021792233","https://openalex.org/W3033185959","https://openalex.org/W3034824379","https://openalex.org/W3045004532","https://openalex.org/W3081886688","https://openalex.org/W3097667802","https://openalex.org/W3109304495","https://openalex.org/W3119002307","https://openalex.org/W3213213154","https://openalex.org/W4205206694","https://openalex.org/W4210791946","https://openalex.org/W4225139287","https://openalex.org/W4280591423","https://openalex.org/W4297102408","https://openalex.org/W4312252005","https://openalex.org/W4313413039","https://openalex.org/W4321383745","https://openalex.org/W4367043271","https://openalex.org/W4391164176","https://openalex.org/W4401506251","https://openalex.org/W6636510571","https://openalex.org/W6691431627","https://openalex.org/W6755207826","https://openalex.org/W6857420318"],"related_works":["https://openalex.org/W2389818373","https://openalex.org/W4392445444","https://openalex.org/W4396220545","https://openalex.org/W2220831889","https://openalex.org/W4312683641","https://openalex.org/W3027421045","https://openalex.org/W4405933298","https://openalex.org/W3013312691","https://openalex.org/W2980386803","https://openalex.org/W3215994059"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"optimizing":[3],"classification":[4,90],"pipelines":[5],"has":[6],"become":[7],"increasingly":[8],"critical":[9],"due":[10],"to":[11,111,160],"the":[12,19,35,56,61,77,86,101,150,153],"growing":[13],"volume":[14],"of":[15,43,60,89,152],"textual":[16,71],"data":[17],"and":[18,51,106,134,139,141],"computational":[20],"challenges":[21],"associated":[22],"with":[23,117],"exhaustive":[24,115,172],"hyperparameter":[25,161],"tuning.":[26],"This":[27],"paper":[28],"proposes":[29],"a":[30,127,142,157],"similarity-based":[31,102],"approach":[32,103],"for":[33,137,145,169],"selecting":[34],"most":[36],"promising":[37],"vectorization":[38,164],"configurations":[39,66],"\u2013":[40,53],"specifically,":[41],"Bag":[42],"Words":[44],"(BoW),":[45],"Term":[46],"Frequency-Inverse":[47],"Document":[48],"Frequency":[49],"(TF-IDF),":[50],"Word2Vec":[52],"by":[54,64],"analyzing":[55],"average":[57],"cosine":[58],"similarity":[59,133],"generated":[62],"vectors;":[63],"preselecting":[65],"that":[67,79,100],"yield":[68],"more":[69],"diverse":[70],"representations,":[72],"our":[73],"method":[74,155],"relies":[75],"on":[76,95],"hypothesis":[78],"increased":[80],"diversity":[81],"in":[82,120,163],"text":[83],"representations":[84],"enhances":[85],"discriminative":[87],"capacity":[88],"models.":[91],"Experimental":[92],"evaluations":[93],"conducted":[94],"five":[96],"different":[97],"datasets":[98],"demonstrate":[99],"achieves":[104],"accuracy":[105],"F1-Score":[107],"results":[108],"very":[109],"close":[110],"those":[112],"obtained":[113],"via":[114],"search,":[116],"notable":[118],"reductions":[119],"processing":[121],"time;":[122],"furthermore,":[123],"correlation":[124],"analyses":[125],"reveal":[126],"strong":[128],"inverse":[129],"relationship":[130,144],"between":[131],"vector":[132],"model":[135],"performance":[136],"BoW":[138],"TF-IDF,":[140],"moderate":[143],"Word2Vec.":[146],"These":[147],"findings":[148],"validate":[149],"efficacy":[151],"proposed":[154],"as":[156],"practical":[158],"alternative":[159],"selection":[162],"pipelines,":[165],"offering":[166],"significant":[167],"benefits":[168],"applications":[170],"where":[171],"exploration":[173],"is":[174],"unfeasible.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}