{"id":"https://openalex.org/W4391403964","doi":"https://doi.org/10.3390/info15020077","title":"Comparative Analysis of NLP-Based Models for Company Classification","display_name":"Comparative Analysis of NLP-Based Models for Company Classification","publication_year":2024,"publication_date":"2024-01-31","ids":{"openalex":"https://openalex.org/W4391403964","doi":"https://doi.org/10.3390/info15020077"},"language":"en","primary_location":{"id":"doi:10.3390/info15020077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15020077","pdf_url":"https://www.mdpi.com/2078-2489/15/2/77/pdf?version=1706687657","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/15/2/77/pdf?version=1706687657","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054465893","display_name":"Maryan Rizinski","orcid":"https://orcid.org/0000-0002-9324-0091"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I76245029","display_name":"Saints Cyril and Methodius University of Skopje","ror":"https://ror.org/02wk2vx54","country_code":"MK","type":"education","lineage":["https://openalex.org/I76245029"]}],"countries":["MK","US"],"is_corresponding":true,"raw_author_name":"Maryan Rizinski","raw_affiliation_strings":["Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA","Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia","institution_ids":["https://openalex.org/I76245029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079879709","display_name":"Andrej Jankov","orcid":"https://orcid.org/0009-0002-9787-3731"},"institutions":[{"id":"https://openalex.org/I76245029","display_name":"Saints Cyril and Methodius University of Skopje","ror":"https://ror.org/02wk2vx54","country_code":"MK","type":"education","lineage":["https://openalex.org/I76245029"]}],"countries":["MK"],"is_corresponding":false,"raw_author_name":"Andrej Jankov","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia","institution_ids":["https://openalex.org/I76245029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025317709","display_name":"Vignesh Sankaradas","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vignesh Sankaradas","raw_affiliation_strings":["Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023669249","display_name":"Eugene Pinsky","orcid":"https://orcid.org/0000-0002-3836-1851"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Pinsky","raw_affiliation_strings":["Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037207344","display_name":"Igor Mishkovski","orcid":"https://orcid.org/0000-0003-1137-6102"},"institutions":[{"id":"https://openalex.org/I76245029","display_name":"Saints Cyril and Methodius University of Skopje","ror":"https://ror.org/02wk2vx54","country_code":"MK","type":"education","lineage":["https://openalex.org/I76245029"]}],"countries":["MK"],"is_corresponding":false,"raw_author_name":"Igor Mishkovski","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia","institution_ids":["https://openalex.org/I76245029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067143303","display_name":"Dimitar Trajanov","orcid":"https://orcid.org/0000-0002-3105-6010"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I76245029","display_name":"Saints Cyril and Methodius University of Skopje","ror":"https://ror.org/02wk2vx54","country_code":"MK","type":"education","lineage":["https://openalex.org/I76245029"]}],"countries":["MK","US"],"is_corresponding":true,"raw_author_name":"Dimitar Trajanov","raw_affiliation_strings":["Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA","Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia","institution_ids":["https://openalex.org/I76245029"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054465893","https://openalex.org/A5067143303"],"corresponding_institution_ids":["https://openalex.org/I111088046","https://openalex.org/I76245029"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":4.004,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93261351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"15","issue":"2","first_page":"77","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10081","display_name":"Auditing, Earnings Management, Governance","score":0.9682000279426575,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9634000062942505,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6846753358840942},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5665661692619324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5319521427154541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3200075030326843}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6846753358840942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5665661692619324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5319521427154541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3200075030326843}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info15020077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15020077","pdf_url":"https://www.mdpi.com/2078-2489/15/2/77/pdf?version=1706687657","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:null:2144/50169","is_oa":true,"landing_page_url":"https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=elements-bu-prod&SrcAuth=WosAPI&KeyUT=WOS:001170107200001&DestLinkType=FullRecord&DestApp=WOS_CPL","pdf_url":null,"source":{"id":"https://openalex.org/S4306402384","display_name":"OpenBU (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:40d33d9cfd374735ac61c1237bb98d74","is_oa":true,"landing_page_url":"https://doaj.org/article/40d33d9cfd374735ac61c1237bb98d74","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 15, Iss 2, p 77 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info15020077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15020077","pdf_url":"https://www.mdpi.com/2078-2489/15/2/77/pdf?version=1706687657","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5799999833106995,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391403964.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1541477479","https://openalex.org/W2047134779","https://openalex.org/W2063404424","https://openalex.org/W2071791836","https://openalex.org/W2087681420","https://openalex.org/W2128792405","https://openalex.org/W2129906471","https://openalex.org/W2142047467","https://openalex.org/W2160442388","https://openalex.org/W2208635417","https://openalex.org/W2294675754","https://openalex.org/W2307376191","https://openalex.org/W2583353385","https://openalex.org/W2728831081","https://openalex.org/W2782592172","https://openalex.org/W2785939461","https://openalex.org/W2802787326","https://openalex.org/W2804820865","https://openalex.org/W2888750492","https://openalex.org/W2937423263","https://openalex.org/W2949351602","https://openalex.org/W2969886070","https://openalex.org/W2975867066","https://openalex.org/W2979826702","https://openalex.org/W2991598420","https://openalex.org/W3010232169","https://openalex.org/W3022746105","https://openalex.org/W3034563984","https://openalex.org/W3043424630","https://openalex.org/W3082059448","https://openalex.org/W3087322177","https://openalex.org/W3104422614","https://openalex.org/W3105625590","https://openalex.org/W3124462827","https://openalex.org/W3124977889","https://openalex.org/W3125902221","https://openalex.org/W3134336972","https://openalex.org/W3175157820","https://openalex.org/W3181204626","https://openalex.org/W3198357836","https://openalex.org/W3215782175","https://openalex.org/W4205344122","https://openalex.org/W4210610208","https://openalex.org/W4212791338","https://openalex.org/W4310248870","https://openalex.org/W4312884634","https://openalex.org/W4321504495","https://openalex.org/W4381948376","https://openalex.org/W4385570594","https://openalex.org/W4390591112","https://openalex.org/W6697942893"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,89],"task":[1],"of":[2,100,103,123,202,228],"company":[3,50,86,203,233],"classification":[4,51,87,148,165,234],"is":[5],"traditionally":[6],"performed":[7],"using":[8],"established":[9],"standards,":[10],"such":[11],"as":[12],"the":[13,49,85,92,111,117,128,140,163,169,217,226,232],"Global":[14],"Industry":[15],"Classification":[16],"Standard":[17],"(GICS).":[18],"However,":[19],"these":[20,78],"approaches":[21],"heavily":[22],"rely":[23],"on":[24,127,231],"laborious":[25],"manual":[26],"efforts":[27],"by":[28,221],"domain":[29],"experts,":[30],"resulting":[31],"in":[32,84,150,168,182,198,216],"slow,":[33],"costly,":[34],"and":[35,57,69,113,125,145,153,207],"vendor-specific":[36],"assignments.":[37],"Therefore,":[38],"we":[39,55,158,172,190,209],"investigate":[40],"recent":[41],"natural":[42],"language":[43],"processing":[44],"(NLP)":[45],"advancements":[46],"to":[47,80,142,162,175,184,213,224],"automate":[48],"process.":[52],"In":[53,156],"particular,":[54],"employ":[56,211],"evaluate":[58],"various":[59],"NLP-based":[60],"models,":[61],"including":[62],"zero-shot":[63,170,186],"learning,":[64],"One-vs-Rest":[65,114],"classification,":[66],"multi-class":[67,164],"classifiers,":[68],"ChatGPT-aided":[70],"classification.":[71],"We":[72],"conduct":[73],"a":[74],"comprehensive":[75],"comparison":[76,183],"among":[77],"models":[79],"assess":[81,225],"their":[82],"effectiveness":[83],"task.":[88],"evaluation":[90],"uses":[91],"Wharton":[93],"Research":[94],"Data":[95],"Services":[96],"(WRDS)":[97],"dataset,":[98,130,219],"consisting":[99],"textual":[101],"descriptions":[102,204],"publicly":[104],"traded":[105],"companies.":[106],"Our":[107],"findings":[108],"reveal":[109],"that":[110,135],"RoBERTa":[112],"classifiers":[115],"surpass":[116],"other":[118],"methods,":[119],"achieving":[120],"F1":[121],"scores":[122],"0.81":[124],"0.80":[126],"WRDS":[129,218],"respectively.":[131],"These":[132],"results":[133],"demonstrate":[134],"deep":[136],"learning":[137],"algorithms":[138],"offer":[139],"potential":[141,197],"automate,":[143],"standardize,":[144],"continuously":[146],"update":[147],"systems":[149],"an":[151],"efficient":[152],"cost-effective":[154],"way.":[155],"addition,":[157],"introduce":[159],"several":[160],"improvements":[161],"techniques:":[166],"(1)":[167],"methodology,":[171],"use":[173,191],"TF-IDF":[174],"enhance":[176],"sector":[177],"representation,":[178],"yielding":[179],"improved":[180],"accuracy":[181],"standard":[185],"classifiers;":[187],"(2)":[188],"next,":[189],"ChatGPT":[192],"for":[193],"dataset":[194],"generation,":[195],"revealing":[196],"scenarios":[199],"where":[200],"datasets":[201],"are":[205],"lacking;":[206],"(3)":[208],"also":[210],"K-Fold":[212],"reduce":[214],"noise":[215,229],"followed":[220],"conducting":[222],"experiments":[223],"impact":[227],"reduction":[230],"results.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}