{"id":"https://openalex.org/W7087648452","doi":"https://doi.org/10.18420/inf2025_89","title":"Record Linkage for Historical German VET Data: Towards Linked Labor Market Data","display_name":"Record Linkage for Historical German VET Data: Towards Linked Labor Market Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7087648452","doi":"https://doi.org/10.18420/inf2025_89"},"language":"en","primary_location":{"id":"doi:10.18420/inf2025_89","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2025_89","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/inf2025_89","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Reiser, Thomas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Reiser, Thomas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"D\u00f6rpinghaus, Jens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D\u00f6rpinghaus, Jens","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Steiner, Petra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steiner, Petra","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59503845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9147999882698059,"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/T11719","display_name":"Data Quality and Management","score":0.9147999882698059,"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/T11937","display_name":"Research Data Management Practices","score":0.02669999934732914,"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/T14330","display_name":"Library Science and Information Systems","score":0.007000000216066837,"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/record-linkage","display_name":"Record linkage","score":0.8264999985694885},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6567000150680542},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6416000127792358},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5814999938011169},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.5501999855041504},{"id":"https://openalex.org/keywords/vocational-education","display_name":"Vocational education","score":0.5336999893188477},{"id":"https://openalex.org/keywords/historical-record","display_name":"Historical record","score":0.43779999017715454}],"concepts":[{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.8264999985694885},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6567000150680542},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6416000127792358},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.5501999855041504},{"id":"https://openalex.org/C668760","wikidata":"https://www.wikidata.org/wiki/Q6869278","display_name":"Vocational education","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C53553401","wikidata":"https://www.wikidata.org/wiki/Q47307","display_name":"Genealogy","level":1,"score":0.5055999755859375},{"id":"https://openalex.org/C2992790187","wikidata":"https://www.wikidata.org/wiki/Q1145106","display_name":"Historical record","level":3,"score":0.43779999017715454},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.4277999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38510000705718994},{"id":"https://openalex.org/C2780902518","wikidata":"https://www.wikidata.org/wiki/Q6033780","display_name":"Inheritance (genetic algorithm)","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.30000001192092896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C2987726880","wikidata":"https://www.wikidata.org/wiki/Q517656","display_name":"Records management","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.27559998631477356},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C178005623","wikidata":"https://www.wikidata.org/wiki/Q308859","display_name":"Anonymity","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C3019724377","wikidata":"https://www.wikidata.org/wiki/Q517656","display_name":"Record keeping","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/inf2025_89","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2025_89","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/inf2025_89","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2025_89","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6577377915382385}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Digital":[0],"archives":[1,42],"often":[2],"describe":[3,31],"their":[4],"catalogs":[5],"with":[6,90],"digital":[7],"objects":[8],"where":[9,43],"each":[10],"record":[11,69,101,120,188],"represents":[12],"a":[13,118,141],"physical":[14],"document":[15],"that":[16,33,56,99,131,181,193],"can":[17,49,57],"be":[18,58,183],"found":[19],"in":[20,36,113,121,166],"the":[21,37,44,62,73,76,80,91,103,108,122,128,133,136,144,194,195],"archive.":[22],"While":[23],"this":[24,149],"is":[25,27,34,98],"approach":[26,54],"most":[28],"effective":[29],"to":[30,60,177,185],"data":[32,146,161],"present":[35],"archive,":[38,66],"there":[39],"are":[40,174],"some":[41,203],"absence":[45],"of":[46,64,75,93,110,154,159],"missing":[47],"documents":[48],"impact":[50],"its":[51],"quality.":[52],"To":[53,148],"methods":[55,71],"used":[59,176],"assess":[61],"completeness":[63],"an":[65],"we":[67,151],"use":[68],"linkage":[70],"on":[72],"example":[74],"occupations":[77,123],"archive":[78,124],"at":[79],"Federal":[81],"Institute":[82],"for":[83,135,206],"Vocational":[84],"Education":[85],"and":[86,163,170],"Training":[87],"(BIBB),":[88],"combined":[89],"genealogy":[92,104,137],"vocational":[94,111],"education.":[95],"Our":[96],"idea":[97],"every":[100],"from":[102],"\u2013":[105,115,125,138],"which":[106,126,139],"describes":[107],"history":[109],"training":[112],"Germany":[114],"should":[116,182],"have":[117],"matching":[119],"contains":[127],"legal":[129],"regulations":[130],"build":[132],"foundation":[134],"implies":[140],"mapping":[142],"between":[143,157],"two":[145,167],"sets.":[147],"end,":[150],"create":[152],"pairs":[153,173],"potential":[155],"matches":[156,169],"records":[158],"both":[160],"sets":[162],"separate":[164],"them":[165],"classes:":[168],"non-matches.":[171],"These":[172],"then":[175],"train":[178],"different":[179],"classifiers":[180,197],"able":[184],"categorize":[186],"unseen":[187],"pairs.":[189],"The":[190],"results":[191,200],"show":[192],"selected":[196],"give":[198],"reasonable":[199],"but":[201],"need":[202],"more":[204],"improvements":[205],"better":[207],"reliability.":[208]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-11T00:00:00"}
