{"id":"https://openalex.org/W4408274215","doi":"https://doi.org/10.1007/s11192-025-05244-y","title":"A large-scale semi-automated approach for assessing document-type classification errors in bibliometric databases","display_name":"A large-scale semi-automated approach for assessing document-type classification errors in bibliometric databases","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4408274215","doi":"https://doi.org/10.1007/s11192-025-05244-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11192-025-05244-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-025-05244-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11192-025-05244-y.pdf","source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","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":"Scientometrics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11192-025-05244-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077578200","display_name":"Domenico Maisano","orcid":"https://orcid.org/0000-0002-8154-4469"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"D. A. Maisano","raw_affiliation_strings":["Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065075538","display_name":"Luca Mastrogiacomo","orcid":"https://orcid.org/0000-0002-8454-5918"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"L. Mastrogiacomo","raw_affiliation_strings":["Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007070312","display_name":"Lorenzo Ferrara","orcid":"https://orcid.org/0000-0002-6157-3369"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"L. Ferrara","raw_affiliation_strings":["Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076149889","display_name":"Fiorenzo Franceschini","orcid":"https://orcid.org/0000-0001-7131-4419"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"F. Franceschini","raw_affiliation_strings":["Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Management and Production Engineering (DIGEP), Politecnico Di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077578200"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":10.8665,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"130","issue":"3","first_page":"1901","last_page":"1938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/T10102","display_name":"scientometrics and bibliometrics research","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9241999983787537,"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/computer-science","display_name":"Computer science","score":0.6147394180297852},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5973026156425476},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5802347660064697},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4773159921169281},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.45545074343681335},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3899920582771301},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33259129524230957},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18520578742027283},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1196494996547699},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07797837257385254},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.0750894546508789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147394180297852},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5973026156425476},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5802347660064697},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4773159921169281},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.45545074343681335},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3899920582771301},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33259129524230957},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18520578742027283},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1196494996547699},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07797837257385254},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.0750894546508789},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11192-025-05244-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-025-05244-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11192-025-05244-y.pdf","source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","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":"Scientometrics","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:spr:scient:v:130:y:2025:i:3:d:10.1007_s11192-025-05244-y","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s11192-025-05244-y","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s11192-025-05244-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-025-05244-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11192-025-05244-y.pdf","source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","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":"Scientometrics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313985","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408274215.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1546460521","https://openalex.org/W1920360620","https://openalex.org/W2007482872","https://openalex.org/W2112256138","https://openalex.org/W2124106033","https://openalex.org/W2126622095","https://openalex.org/W2142182511","https://openalex.org/W2520427567","https://openalex.org/W2593559024","https://openalex.org/W2744152618","https://openalex.org/W2968486945","https://openalex.org/W3216173529","https://openalex.org/W4214770604","https://openalex.org/W4250137533","https://openalex.org/W4285325349","https://openalex.org/W4300997486","https://openalex.org/W4377247651","https://openalex.org/W4391947463","https://openalex.org/W4399991117","https://openalex.org/W4404210278","https://openalex.org/W6808003095"],"related_works":["https://openalex.org/W2003932708","https://openalex.org/W1967424056","https://openalex.org/W2284877871","https://openalex.org/W2138102289","https://openalex.org/W868043274","https://openalex.org/W2513523087","https://openalex.org/W1187916458","https://openalex.org/W2373861055","https://openalex.org/W1559716973","https://openalex.org/W3109364360"],"abstract_inverted_index":{"Abstract":[0],"The":[1,70,86,123,148,163],"accuracy":[2,55],"of":[3,56,67,89,130,133,135,141,154,171,180,192],"bibliometric":[4,35,60],"databases":[5],"in":[6,59,95,102,145,174,189],"classifying":[7],"document":[8,75],"types":[9,170],"(DTs)\u2014such":[10],"as":[11,34,63],"research":[12,40],"articles":[13],",":[14,17,19,22,24,27],"conference":[15],"proceedings":[16],"reviews":[18],"short":[20],"notes":[21],"letters":[23],"book":[25],"chapters":[26],"etc.\u2014is":[28],"crucial":[29],"for":[30,157,161,186],"the":[31,54,90,109,138,167,190],"academic":[32,44],"community,":[33],"indicators":[36],"may":[37],"significantly":[38],"influence":[39],"funding,":[41],"decision-making,":[42],"and":[43,65,77,100,119,159,183],"reputation.":[45],"This":[46],"study":[47],"presents":[48],"a":[49,128],"semi-automated":[50],"methodology":[51,71,91,124],"to":[52,79,104,117,127],"assess":[53],"DT":[57,81,96],"classification":[58,121],"databases,":[61,176],"such":[62],"Scopus":[64,99,158],"Web":[66],"Science":[68],"(WoS).":[69],"can":[72],"handle":[73],"large":[74],"volumes":[76],"adapt":[78],"different":[80],"categories":[82],"without":[83],"predefined":[84],"correspondences.":[85],"first":[87],"phase":[88,111],"automatically":[92],"identifies":[93],"discrepancies":[94],"classifications":[97],"between":[98],"WoS,":[101],"order":[103],"find":[105],"potentially":[106],"misclassified":[107],"documents;":[108],"second":[110],"involves":[112],"manually":[113],"analyzing":[114],"these":[115,181,193],"documents":[116],"confirm":[118],"attribute":[120],"errors.":[122],"is":[125],"applied":[126],"sample":[129],"several":[131],"tens":[132],"thousands":[134],"papers":[136],"from":[137],"teaching":[139],"staff":[140],"two":[142],"major":[143],"universities":[144],"Turin":[146],"(Italy).":[147],"results":[149],"show":[150],"overall":[151],"error":[152],"rates":[153],"approximately":[155],"2.7%":[156],"2.3%":[160],"WoS.":[162],"paper":[164],"also":[165],"analyzes":[166],"most":[168],"common":[169],"errors":[172],"found":[173],"both":[175],"providing":[177],"an":[178],"interpretation":[179],"inaccuracies":[182],"some":[184],"insights":[185],"possible":[187],"improvements":[188],"quality":[191],"databases.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
