{"id":"https://openalex.org/W4318147135","doi":"https://doi.org/10.1109/bigdata55660.2022.10020787","title":"Applying NLP Techniques to Classify Businesses by their International Standard Industrial Classification (ISIC) Code","display_name":"Applying NLP Techniques to Classify Businesses by their International Standard Industrial Classification (ISIC) Code","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318147135","doi":"https://doi.org/10.1109/bigdata55660.2022.10020787"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020787","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020787","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053920341","display_name":"Hannah B\u00e9chara","orcid":null},"institutions":[{"id":"https://openalex.org/I24830596","display_name":"Hertie School","ror":"https://ror.org/0473a4773","country_code":"DE","type":"education","lineage":["https://openalex.org/I24830596"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hannah Bechara","raw_affiliation_strings":["Hertie School,Data Science Lab,Berlin,Germany","Data Science Lab, Hertie School, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hertie School,Data Science Lab,Berlin,Germany","institution_ids":["https://openalex.org/I24830596"]},{"raw_affiliation_string":"Data Science Lab, Hertie School, Berlin, Germany","institution_ids":["https://openalex.org/I24830596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114500347","display_name":"Ran Zhang","orcid":"https://orcid.org/0009-0000-0708-5287"},"institutions":[{"id":"https://openalex.org/I24830596","display_name":"Hertie School","ror":"https://ror.org/0473a4773","country_code":"DE","type":"education","lineage":["https://openalex.org/I24830596"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ran Zhang","raw_affiliation_strings":["Hertie School,Data Science Lab,Berlin,Germany","Data Science Lab, Hertie School, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hertie School,Data Science Lab,Berlin,Germany","institution_ids":["https://openalex.org/I24830596"]},{"raw_affiliation_string":"Data Science Lab, Hertie School, Berlin, Germany","institution_ids":["https://openalex.org/I24830596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008824325","display_name":"Shuzhou Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shuzhou Yuan","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT),Karlsruhe,Germany","Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT),Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":null,"display_name":"Slava Jankin","orcid":null},"institutions":[{"id":"https://openalex.org/I24830596","display_name":"Hertie School","ror":"https://ror.org/0473a4773","country_code":"DE","type":"education","lineage":["https://openalex.org/I24830596"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Slava Jankin","raw_affiliation_strings":["Hertie School,Data Science Lab,Berlin,Germany","Data Science Lab, Hertie School, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hertie School,Data Science Lab,Berlin,Germany","institution_ids":["https://openalex.org/I24830596"]},{"raw_affiliation_string":"Data Science Lab, Hertie School, Berlin, Germany","institution_ids":["https://openalex.org/I24830596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3472","last_page":"3477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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":0.9988999962806702,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9970999956130981,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9954000115394592,"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/task","display_name":"Task (project management)","score":0.7356745004653931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7336915731430054},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6691815853118896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6507657766342163},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4899705946445465},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"Multiclass classification","score":0.4880143702030182},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4219732880592346},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.19946053624153137},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1101427674293518},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07524600625038147}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7356745004653931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336915731430054},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6691815853118896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6507657766342163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4899705946445465},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.4880143702030182},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4219732880592346},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.19946053624153137},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1101427674293518},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07524600625038147},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020787","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020787","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"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":32,"referenced_works":["https://openalex.org/W123239138","https://openalex.org/W2064675550","https://openalex.org/W2138524604","https://openalex.org/W2154571511","https://openalex.org/W2607303097","https://openalex.org/W2895919385","https://openalex.org/W2896457183","https://openalex.org/W2970597249","https://openalex.org/W2972633403","https://openalex.org/W2978017171","https://openalex.org/W2983680039","https://openalex.org/W3042609801","https://openalex.org/W3093070113","https://openalex.org/W3101118213","https://openalex.org/W3103304304","https://openalex.org/W3153404013","https://openalex.org/W3156669901","https://openalex.org/W3174726724","https://openalex.org/W3184133963","https://openalex.org/W3197365868","https://openalex.org/W4242995741","https://openalex.org/W4243162485","https://openalex.org/W4287824654","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6768851824","https://openalex.org/W6771917389","https://openalex.org/W6779784029","https://openalex.org/W6780530918","https://openalex.org/W6783801217"],"related_works":["https://openalex.org/W2389815730","https://openalex.org/W2470590370","https://openalex.org/W1537592868","https://openalex.org/W2215801697","https://openalex.org/W2144252306","https://openalex.org/W1629394991","https://openalex.org/W2961085424","https://openalex.org/W3150942535","https://openalex.org/W2385742154","https://openalex.org/W2905251838"],"abstract_inverted_index":{"The":[0],"application":[1,39],"of":[2,13,29,40,66,73,79],"machine":[3],"learning":[4],"has":[5,19],"played":[6],"an":[7],"important":[8],"role":[9],"in":[10],"several":[11,85],"aspects":[12],"text":[14],"classification":[15,116],"across":[16],"domains,":[17],"and":[18,63,75,89],"brought":[20],"with":[21,70,106],"it":[22],"great":[23],"changes":[24],"to":[25,43],"the":[26,30,59,64,71,100],"current":[27],"state":[28],"art.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,83],"propose":[36],"a":[37,76,107,112],"novel":[38],"NLP":[41,87],"techniques":[42],"classify":[44],"entities":[45],"by":[46,58],"their":[47],"International":[48],"Standard":[49],"Industrial":[50],"Classification":[51],"(ISIC)":[52],"code":[53],"based":[54],"on":[55,111],"descriptions":[56],"provided":[57],"business":[60],"owners":[61],"themselves":[62],"names":[65],"said":[67],"businesses.":[68],"Faced":[69],"issues":[72],"irregularity":[74],"small":[77],"amount":[78],"noisy":[80],"training":[81],"data,":[82],"employ":[84],"different":[86],"models":[88],"data":[90],"enhancement":[91],"strategies.":[92],"We":[93],"identify":[94],"DistilBERT,":[95],"under":[96],"normalized":[97],"loss,":[98],"as":[99],"best":[101],"model":[102],"for":[103],"our":[104],"task,":[105],"77.9%":[108],"average":[109],"accuracy":[110],"56":[113],"label":[114],"multiclass":[115],"task.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}