{"id":"https://openalex.org/W4320485489","doi":"https://doi.org/10.1007/s44163-023-00050-y","title":"Automated occupation coding with hierarchical features: a data-centric approach to classification with pre-trained language models","display_name":"Automated occupation coding with hierarchical features: a data-centric approach to classification with pre-trained language models","publication_year":2023,"publication_date":"2023-02-13","ids":{"openalex":"https://openalex.org/W4320485489","doi":"https://doi.org/10.1007/s44163-023-00050-y"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-023-00050-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-023-00050-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-023-00050-y.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44163-023-00050-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019368163","display_name":"Parisa Safikhani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111137","display_name":"German Centre for Higher Education Research and Science Studies","ror":"https://ror.org/01n8j6z65","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210111137"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Parisa Safikhani","raw_affiliation_strings":["German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany","institution_ids":["https://openalex.org/I4210111137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035293330","display_name":"Hayastan Avetisyan","orcid":"https://orcid.org/0000-0003-1186-5985"},"institutions":[{"id":"https://openalex.org/I4210111137","display_name":"German Centre for Higher Education Research and Science Studies","ror":"https://ror.org/01n8j6z65","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210111137"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hayastan Avetisyan","raw_affiliation_strings":["German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany","institution_ids":["https://openalex.org/I4210111137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018478671","display_name":"Dennis F\u00f6ste-Eggers","orcid":"https://orcid.org/0000-0001-6109-2373"},"institutions":[{"id":"https://openalex.org/I4210111137","display_name":"German Centre for Higher Education Research and Science Studies","ror":"https://ror.org/01n8j6z65","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210111137"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dennis F\u00f6ste-Eggers","raw_affiliation_strings":["German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany","institution_ids":["https://openalex.org/I4210111137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061367729","display_name":"David Broneske","orcid":"https://orcid.org/0000-0002-9580-740X"},"institutions":[{"id":"https://openalex.org/I4210111137","display_name":"German Centre for Higher Education Research and Science Studies","ror":"https://ror.org/01n8j6z65","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210111137"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Broneske","raw_affiliation_strings":["German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Centre for Higher Education Research and Science Studies (DZHW), Lange Laube 12, 30159, Hannover, Lower Saxony, Germany","institution_ids":["https://openalex.org/I4210111137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5019368163"],"corresponding_institution_ids":["https://openalex.org/I4210111137"],"apc_list":{"value":1340,"currency":"USD","value_usd":1340},"apc_paid":{"value":1340,"currency":"USD","value_usd":1340},"fwci":3.2769,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91972972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10235","display_name":"Health disparities and outcomes","score":0.8615000247955322,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10235","display_name":"Health disparities and outcomes","score":0.8615000247955322,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.751531183719635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7030923366546631},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5933154225349426},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5496205687522888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45664024353027344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34888556599617004},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11340969800949097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09403404593467712}],"concepts":[{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.751531183719635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7030923366546631},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5933154225349426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5496205687522888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45664024353027344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34888556599617004},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11340969800949097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09403404593467712}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44163-023-00050-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-023-00050-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-023-00050-y.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b9ec399204854c6ea310b1d1e1f43cc9","is_oa":true,"landing_page_url":"https://doaj.org/article/b9ec399204854c6ea310b1d1e1f43cc9","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":"Discover Artificial Intelligence, Vol 3, Iss 1, Pp 1-12 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44163-023-00050-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-023-00050-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-023-00050-y.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4320485489.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1599774589","https://openalex.org/W2012256356","https://openalex.org/W2071841567","https://openalex.org/W2073617979","https://openalex.org/W2103718426","https://openalex.org/W2591159053","https://openalex.org/W2804950989","https://openalex.org/W2913139235","https://openalex.org/W2981852735","https://openalex.org/W3035066987","https://openalex.org/W3037636001","https://openalex.org/W3048450859","https://openalex.org/W3095319910","https://openalex.org/W3095502049","https://openalex.org/W3114950584","https://openalex.org/W3156333129","https://openalex.org/W3209399758","https://openalex.org/W4200399640","https://openalex.org/W6602368977","https://openalex.org/W6702248584","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Abstract":[0],"Occupation":[1,19],"coding":[2,20,107],"is":[3,11,21],"the":[4,14,42,45,60,114,118,131],"classification":[5,132],"of":[6,16,44,62,108,117,133],"information":[7],"on":[8],"occupation":[9],"that":[10,36,87,126],"collected":[12],"in":[13,30,94],"context":[15],"demographic":[17],"variables.":[18],"an":[22,124],"important,":[23],"but":[24,101],"a":[25,91],"tedious":[26],"task":[27],"for":[28,38,104,130],"researchers":[29,48],"social":[31],"science":[32],"and":[33],"official":[34],"statistics":[35],"calls":[37],"automation.":[39],"Due":[40],"to":[41,98],"complexity":[43],"task,":[46],"currently,":[47],"carry":[49],"out":[50],"hand-coding":[51,66],"or":[52,75],"computer-assisted":[53],"coding.":[54],"However,":[55],"we":[56,78,121],"argue":[57],"that,":[58],"with":[59,82],"rise":[61],"transformer-based":[63],"language":[64,88],"models,":[65,71],"can":[67],"be":[68],"displaced":[69],"by":[70],"such":[72],"as":[73],"BERT":[74],"GPT3.":[76],"Hence,":[77],"compare":[79],"these":[80],"models":[81,89],"state-of-the-art":[83],"encoding":[84],"approaches,":[85,100],"showing":[86],"have":[90],"clear":[92],"advantage":[93],"Cohen\u2019s":[95],"kappa":[96],"compared":[97],"related":[99],"also":[102,122],"allow":[103],"flexible":[105],"fine-grained":[106],"single":[109,135],"digits.":[110],"Taking":[111],"into":[112],"consideration":[113],"hierarchical":[115],"structure":[116],"occupational":[119],"group,":[120],"develop":[123],"approach":[125],"achieves":[127],"better":[128],"performance":[129],"different":[134],"digit":[136],"combinations.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}