{"id":"https://openalex.org/W4390188452","doi":"https://doi.org/10.1109/iit59782.2023.10366487","title":"Enabling Digital Transformation through Business Text Classification with Small Datasets","display_name":"Enabling Digital Transformation through Business Text Classification with Small Datasets","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4390188452","doi":"https://doi.org/10.1109/iit59782.2023.10366487"},"language":"en","primary_location":{"id":"doi:10.1109/iit59782.2023.10366487","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iit59782.2023.10366487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 15th International Conference on Innovations in Information Technology (IIT)","raw_type":"proceedings-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/A5080371676","display_name":"Muhammad Arslan","orcid":"https://orcid.org/0000-0003-3682-7002"},"institutions":[{"id":"https://openalex.org/I4210124615","display_name":"Laboratoire Interdisciplinaire Carnot de Bourgogne","ror":"https://ror.org/02b6c1039","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I37553959","https://openalex.org/I4210124615","https://openalex.org/I4407990431"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Muhammad Arslan","raw_affiliation_strings":["Université de Bourgogne,Laboratoire Interdisciplinaire Carnot de Bourgogne (ICB),Dijon,France"],"affiliations":[{"raw_affiliation_string":"Université de Bourgogne,Laboratoire Interdisciplinaire Carnot de Bourgogne (ICB),Dijon,France","institution_ids":["https://openalex.org/I4210124615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031830209","display_name":"Christophe Cruz","orcid":"https://orcid.org/0000-0002-5611-9479"},"institutions":[{"id":"https://openalex.org/I4210124615","display_name":"Laboratoire Interdisciplinaire Carnot de Bourgogne","ror":"https://ror.org/02b6c1039","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I37553959","https://openalex.org/I4210124615","https://openalex.org/I4407990431"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Cruz","raw_affiliation_strings":["Université de Bourgogne,Laboratoire Interdisciplinaire Carnot de Bourgogne (ICB),Dijon,France"],"affiliations":[{"raw_affiliation_string":"Université de Bourgogne,Laboratoire Interdisciplinaire Carnot de Bourgogne (ICB),Dijon,France","institution_ids":["https://openalex.org/I4210124615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080371676"],"corresponding_institution_ids":["https://openalex.org/I4210124615"],"apc_list":null,"apc_paid":null,"fwci":0.1751,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59093572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"38","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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":0.9994000196456909,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9915000200271606,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9868999719619751,"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/computer-science","display_name":"Computer science","score":0.717161238193512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5995208621025085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5425300598144531},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.494398832321167},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49399882555007935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45052841305732727},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.414675235748291},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.38102903962135315},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32355669140815735},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.18860024213790894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717161238193512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5995208621025085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5425300598144531},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.494398832321167},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49399882555007935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45052841305732727},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.414675235748291},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.38102903962135315},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32355669140815735},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.18860024213790894}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iit59782.2023.10366487","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iit59782.2023.10366487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 15th International Conference on Innovations in Information Technology (IIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1964584498","https://openalex.org/W1986159170","https://openalex.org/W1999954155","https://openalex.org/W2093238926","https://openalex.org/W3006352205","https://openalex.org/W3015657179","https://openalex.org/W3095319910","https://openalex.org/W3116949825","https://openalex.org/W3130451294","https://openalex.org/W4224245290","https://openalex.org/W4297035741","https://openalex.org/W4323925572","https://openalex.org/W4380558740","https://openalex.org/W4380763445","https://openalex.org/W4381587368","https://openalex.org/W6853191046","https://openalex.org/W6854064852"],"related_works":["https://openalex.org/W2747895175","https://openalex.org/W2614669534","https://openalex.org/W2104406636","https://openalex.org/W2123014508","https://openalex.org/W2741028958","https://openalex.org/W2105512057","https://openalex.org/W4252625449","https://openalex.org/W3131201603","https://openalex.org/W2115788596","https://openalex.org/W4387784741"],"abstract_inverted_index":{"Digital":[0],"transformation":[1],"represents":[2],"a":[3,22,37,43,78,85,105,134,147],"complex":[4,261],"process":[5],"that":[6],"entails":[7],"the":[8,16,70,96,150,176,196,241,260],"complete":[9],"reconfiguration":[10],"of":[11,19,88,143,179,243,263],"an":[12,65],"organization":[13],"to":[14,26,47],"harness":[15],"full":[17],"potential":[18],"technology":[20],"on":[21,222],"grand":[23],"scale,":[24],"aiming":[25],"deliver":[27],"maximum":[28],"value.":[29],"To":[30,90,111],"illustrate":[31],"this":[32,92],"transformative":[33],"journey,":[34],"we":[35,63,94,114],"present":[36],"real-world":[38],"case":[39],"study":[40],"centered":[41],"around":[42],"company's":[44],"ambitious":[45],"pursuit":[46],"modernize":[48],"its":[49,156],"manual":[50],"business":[51,71],"text":[52,80,101,119,184,247],"classification":[53,120,185,248],"processes":[54],"by":[55,69,98,139],"embracing":[56],"automated":[57],"machine-based":[58],"methods.":[59],"During":[60],"our":[61,144],"endeavor,":[62],"encountered":[64],"imbalanced":[66],"dataset":[67,97],"provided":[68],"company,":[72],"with":[73,190,250],"certain":[74],"categories":[75],"containing":[76],"only":[77],"few":[79],"examples":[81],"while":[82],"others":[83],"had":[84],"substantial":[86],"number":[87],"them.":[89],"rectify":[91],"imbalance,":[93],"balanced":[95],"removing":[99],"excessive":[100],"examples,":[102],"resulting":[103],"in":[104,182,246,259],"more":[106],"manageable":[107],"and":[108,128,166,203,209],"smaller":[109],"dataset.":[110],"use":[112],"it,":[113],"thoroughly":[115],"evaluated":[116],"four":[117],"multilabel":[118],"methods:":[121],"Binary":[122,199],"Relevance,":[123,200],"Classifier":[124,201],"Chains,":[125,202],"Label":[126,204],"Powerset,":[127],"Generative":[129],"Pre-trained":[130],"Transformer":[131],"(GPT)":[132],"i.e.,":[133],"large":[135],"language":[136],"model":[137],"developed":[138],"OpenAI.":[140],"The":[141],"results":[142],"investigation":[145],"unveiled":[146],"success":[148],"for":[149,225,231,257],"GPT-based":[151,180,244],"approach,":[152],"which":[153],"significantly":[154],"outperformed":[155],"counterparts":[157],"across":[158],"vital":[159],"performance":[160,214],"metrics,":[161],"including":[162],"Accuracy,":[163],"F1-Score,":[164],"Precision,":[165],"Recall.":[167],"This":[168],"outcome":[169],"is":[170,236],"particularly":[171],"noteworthy":[172],"because":[173],"it":[174],"showcases":[175],"remarkable":[177],"effectiveness":[178],"models":[181,245],"multi-label":[183],"tasks,":[186],"even":[187],"when":[188],"dealing":[189],"relatively":[191],"small":[192,251],"datasets.":[193],"In":[194],"contrast,":[195],"other":[197],"methods,":[198],"Powerset":[205],"didn't":[206],"demonstrate":[207],"competence":[208],"exhibited":[210],"comparatively":[211],"less":[212,229],"impressive":[213],"levels.":[215],"Notably,":[216],"these":[217],"traditional":[218],"methods":[219],"typically":[220],"rely":[221],"larger":[223],"datasets":[224],"training,":[226],"making":[227,253],"them":[228,254],"suitable":[230],"scenarios":[232],"where":[233],"data":[234],"availability":[235],"limited.":[237],"These":[238],"findings":[239],"underscore":[240],"power":[242],"tasks":[249],"datasets,":[252],"valuable":[255],"assets":[256],"businesses":[258],"landscape":[262],"digital":[264],"transformation.":[265]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}