{"id":"https://openalex.org/W2599579729","doi":"https://doi.org/10.1007/s11192-017-2363-5","title":"Data sets for author name disambiguation: an empirical analysis and a new resource","display_name":"Data sets for author name disambiguation: an empirical analysis and a new resource","publication_year":2017,"publication_date":"2017-03-26","ids":{"openalex":"https://openalex.org/W2599579729","doi":"https://doi.org/10.1007/s11192-017-2363-5","mag":"2599579729","pmid":"https://pubmed.ncbi.nlm.nih.gov/28596627"},"language":"en","primary_location":{"id":"doi:10.1007/s11192-017-2363-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-017-2363-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs11192-017-2363-5.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","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs11192-017-2363-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019874352","display_name":"Mark-Christoph M\u00fcller","orcid":"https://orcid.org/0000-0001-5639-7682"},"institutions":[{"id":"https://openalex.org/I71030271","display_name":"Heidelberg Institute for Theoretical Studies","ror":"https://ror.org/01f7bcy98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I71030271"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mark-Christoph M\u00fcller","raw_affiliation_strings":["Heidelberg Institute for Theoretical Studies, Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5639-7682","affiliations":[{"raw_affiliation_string":"Heidelberg Institute for Theoretical Studies, Heidelberg, Germany","institution_ids":["https://openalex.org/I71030271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014573765","display_name":"Florian Reitz","orcid":"https://orcid.org/0000-0001-6114-3388"},"institutions":[{"id":"https://openalex.org/I89864525","display_name":"Universit\u00e4t Trier","ror":"https://ror.org/02778hg05","country_code":"DE","type":"education","lineage":["https://openalex.org/I89864525"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Reitz","raw_affiliation_strings":["DBLP, Trier, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DBLP, Trier, Germany","institution_ids":["https://openalex.org/I89864525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020075690","display_name":"Nicolas Roy","orcid":"https://orcid.org/0000-0003-2463-1408"},"institutions":[{"id":"https://openalex.org/I158675288","display_name":"FIZ Karlsruhe \u2013 Leibniz Institute for Information Infrastructure","ror":"https://ror.org/0387prb75","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I158675288","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicolas Roy","raw_affiliation_strings":["Mathematics Department, FIZ Karlsruhe, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics Department, FIZ Karlsruhe, Berlin, Germany","institution_ids":["https://openalex.org/I158675288"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019874352"],"corresponding_institution_ids":["https://openalex.org/I71030271"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":8.0854,"has_fulltext":true,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97513101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"111","issue":"3","first_page":"1467","last_page":"1500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.978600025177002,"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":0.8470232486724854},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6410980820655823},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5654679536819458},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5601633787155151},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.555660605430603},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.526317834854126},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5005965232849121},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.48662838339805603},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.42788833379745483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22871169447898865},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08560311794281006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8470232486724854},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6410980820655823},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5654679536819458},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5601633787155151},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.555660605430603},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.526317834854126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5005965232849121},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.48662838339805603},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.42788833379745483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22871169447898865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08560311794281006},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/s11192-017-2363-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-017-2363-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs11192-017-2363-5.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":"pmid:28596627","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28596627","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientometrics","raw_type":null},{"id":"pmh:oai:RePEc:spr:scient:v:111:y:2017:i:3:d:10.1007_s11192-017-2363-5","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s11192-017-2363-5","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"},{"id":"pmh:oai:europepmc.org:4311392","is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC5438420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:ids-pub.bsz-bw.de:11087","is_oa":true,"landing_page_url":"https://ids-pub.bsz-bw.de/frontdoor/index/index/docId/11087","pdf_url":null,"source":{"id":"https://openalex.org/S4306401750","display_name":"Publication Server of the Institute for German Language (Institute for German Language)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210099471","host_organization_name":"Leibniz Institute for the German Language","host_organization_lineage":["https://openalex.org/I4210099471"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:5438420","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5438420","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientometrics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s11192-017-2363-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-017-2363-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs11192-017-2363-5.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":[{"id":"https://openalex.org/G413419325","display_name":null,"funder_award_id":"SAW-2015-LZI-2","funder_id":"https://openalex.org/F4320334763","funder_display_name":"Leibniz-Gemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320324316","display_name":"Klaus Tschira Stiftung","ror":"https://ror.org/052jep661"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2599579729.pdf","grobid_xml":"https://content.openalex.org/works/W2599579729.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W120053801","https://openalex.org/W134799774","https://openalex.org/W244256367","https://openalex.org/W809740722","https://openalex.org/W1209362753","https://openalex.org/W1496319844","https://openalex.org/W1547987453","https://openalex.org/W1570303087","https://openalex.org/W1907286193","https://openalex.org/W1907949118","https://openalex.org/W1982912387","https://openalex.org/W1987341880","https://openalex.org/W1990976049","https://openalex.org/W1991157445","https://openalex.org/W2000910146","https://openalex.org/W2001804636","https://openalex.org/W2007172042","https://openalex.org/W2011103067","https://openalex.org/W2018353135","https://openalex.org/W2021007296","https://openalex.org/W2056826404","https://openalex.org/W2058259957","https://openalex.org/W2059035258","https://openalex.org/W2080099271","https://openalex.org/W2120623936","https://openalex.org/W2129558264","https://openalex.org/W2130848543","https://openalex.org/W2147107544","https://openalex.org/W2147347208","https://openalex.org/W2158834757","https://openalex.org/W2162337786","https://openalex.org/W2232208664","https://openalex.org/W2405899239","https://openalex.org/W2955415951","https://openalex.org/W3098845338","https://openalex.org/W3105255771","https://openalex.org/W3125468813","https://openalex.org/W4231254446","https://openalex.org/W6677831550"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W3118638206","https://openalex.org/W1983629434","https://openalex.org/W4324271173","https://openalex.org/W3018365851","https://openalex.org/W1967645776","https://openalex.org/W2352227742","https://openalex.org/W2594414941"],"abstract_inverted_index":{"Data":[0],"sets":[1,28],"of":[2,42,49,64,68,81,87,97,116,123,157],"publication":[3],"meta":[4],"data":[5,27,55,109,118,136],"with":[6,83,128],"manually":[7],"disambiguated":[8],"author":[9,17,69,92],"names":[10],"play":[11],"an":[12],"important":[13,26],"role":[14],"in":[15,160],"current":[16],"name":[18],"disambiguation":[19,77],"(AND)":[20],"research.":[21],"We":[22,145],"review":[23],"the":[24,40,95,113,121,134,155,158,164],"most":[25],"used":[29],"so":[30],"far,":[31],"and":[32,37,66,71,78,89,102,120,162],"compare":[33],"their":[34],"respective":[35],"advantages":[36],"shortcomings.":[38],"From":[39],"results":[41,122],"this":[43,117],"review,":[44],"we":[45,100],"derive":[46],"a":[47,84,106,129,148],"set":[48,119,137],"general":[50],"requirements":[51],"to":[52,138],"future":[53],"AND":[54,108,126,161,165],"sets.":[56],"These":[57],"include":[58],"both":[59],"trivial":[60],"requirements,":[61,99],"like":[62,75],"absence":[63],"errors":[65],"preservation":[67],"order,":[70],"more":[72],"substantial":[73],"ones,":[74],"full":[76],"adequate":[79],"representation":[80],"publications":[82],"small":[85],"number":[86],"authors":[88],"highly":[90],"variable":[91],"names.":[93],"On":[94],"basis":[96],"these":[98],"create":[101],"make":[103],"publicly":[104],"available":[105],"new":[107,150],"set,":[110],"SCAD-zbMATH.":[111],"Both":[112],"quantitative":[114],"analysis":[115],"our":[124],"initial":[125],"experiments":[127],"naive":[130],"baseline":[131],"algorithm":[132],"show":[133],"SCAD-zbMATH":[135],"be":[139],"considerably":[140],"different":[141],"from":[142],"existing":[143],"ones.":[144],"consider":[146],"it":[147],"useful":[149],"resource":[151],"that":[152],"will":[153],"challenge":[154],"state":[156],"art":[159],"benefit":[163],"research":[166],"community.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
