{"id":"https://openalex.org/W3173035675","doi":"https://doi.org/10.1177/01655515211018171","title":"Effect of Chinese characters on machine learning for Chinese author name disambiguation: A counterfactual evaluation","display_name":"Effect of Chinese characters on machine learning for Chinese author name disambiguation: A counterfactual evaluation","publication_year":2021,"publication_date":"2021-05-31","ids":{"openalex":"https://openalex.org/W3173035675","doi":"https://doi.org/10.1177/01655515211018171","mag":"3173035675"},"language":"en","primary_location":{"id":"doi:10.1177/01655515211018171","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01655515211018171","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"},"type":"article","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/A5100757432","display_name":"Jinseok Kim","orcid":"https://orcid.org/0000-0001-6481-2065"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinseok Kim","raw_affiliation_strings":["Institute for Research on Innovation & Science, Survey Research Center, School of Information, University of Michigan, USA","School of Information Sciences, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":"https://orcid.org/0000-0001-6481-2065","affiliations":[{"raw_affiliation_string":"Institute for Research on Innovation & Science, Survey Research Center, School of Information, University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076986012","display_name":"Jenna Kim","orcid":"https://orcid.org/0000-0001-7438-448X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenna Kim","raw_affiliation_strings":["Institute for Research on Innovation & Science, Survey Research Center, School of Information, University of Michigan, USA","School of Information Sciences, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":"https://orcid.org/0000-0001-7438-448X","affiliations":[{"raw_affiliation_string":"Institute for Research on Innovation & Science, Survey Research Center, School of Information, University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101891243","display_name":"Jinmo Kim","orcid":"https://orcid.org/0000-0001-8614-917X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinmo Kim","raw_affiliation_strings":["Institute for Research on Innovation & Science, Survey Research Center, School of Information, University of Michigan, USA","School of Information Sciences, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research on Innovation & Science, Survey Research Center, School of Information, University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100757432"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":1.2537,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80562025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"49","issue":"3","first_page":"711","last_page":"725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9945999979972839,"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/T10028","display_name":"Topic Modeling","score":0.9878000020980835,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7765368819236755},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.6436887383460999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6137381196022034},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5459304451942444},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5239146947860718},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5204408764839172},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.46940839290618896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.408961683511734},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19309166073799133}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7765368819236755},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.6436887383460999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6137381196022034},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5459304451942444},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5239146947860718},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5204408764839172},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.46940839290618896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.408961683511734},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19309166073799133},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/01655515211018171","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01655515211018171","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2045160435","display_name":null,"funder_award_id":"1917663","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1690965494","https://openalex.org/W1991157445","https://openalex.org/W2027482947","https://openalex.org/W2028696063","https://openalex.org/W2033626137","https://openalex.org/W2041309207","https://openalex.org/W2058259957","https://openalex.org/W2065858398","https://openalex.org/W2092391499","https://openalex.org/W2098365647","https://openalex.org/W2111082276","https://openalex.org/W2129558264","https://openalex.org/W2131193521","https://openalex.org/W2140918075","https://openalex.org/W2156897283","https://openalex.org/W2196350189","https://openalex.org/W2281739675","https://openalex.org/W2396578102","https://openalex.org/W2599579729","https://openalex.org/W2601885645","https://openalex.org/W2772492596","https://openalex.org/W2791272878","https://openalex.org/W2800112456","https://openalex.org/W2806499703","https://openalex.org/W2883357302","https://openalex.org/W2900221602","https://openalex.org/W2918008835","https://openalex.org/W2962699071","https://openalex.org/W2978215513","https://openalex.org/W2990649609","https://openalex.org/W3098845338","https://openalex.org/W3105255771","https://openalex.org/W3111877007","https://openalex.org/W3128793634","https://openalex.org/W4230983570","https://openalex.org/W4240964231","https://openalex.org/W4244310778","https://openalex.org/W4252247318"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W3025615835","https://openalex.org/W4384133558","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3003410553","https://openalex.org/W3028847759","https://openalex.org/W2393688264"],"abstract_inverted_index":{"Chinese":[0,34,51,72,81,101,113,129],"author":[1,41,47,82,114,130],"names":[2,14,48,83,115,131],"are":[3,52,74,85,103],"known":[4],"to":[5,9,18,62,95,134],"be":[6],"more":[7],"difficult":[8],"disambiguate":[10],"than":[11],"other":[12],"ethnic":[13],"because":[15],"they":[16],"tend":[17,94],"share":[19],"surnames":[20],"and":[21,56,122],"forenames,":[22],"thus":[23],"creating":[24],"many":[25],"homonyms.":[26],"In":[27],"this":[28],"study,":[29],"we":[30],"demonstrate":[31],"how":[32],"using":[33],"characters":[35,73,102],"can":[36,119],"affect":[37],"machine":[38],"learning":[39],"for":[40],"name":[42],"disambiguation.":[43],"For":[44],"analysis,":[45],"15K":[46],"recorded":[49],"in":[50,70,88,105,116,136,138],"transliterated":[53],"into":[54],"English":[55,89],"simplified":[57],"by":[58],"initialising":[59],"their":[60,100],"forenames":[61,93],"create":[63],"counterfactual":[64],"scenarios,":[65],"reflecting":[66],"real-world":[67],"indexing":[68],"practices":[69],"which":[71],"usually":[75],"unavailable.":[76],"The":[77],"results":[78],"show":[79],"that":[80,84,111,132],"highly":[86],"ambiguous":[87],"or":[90],"with":[91],"initialised":[92],"become":[96],"less":[97],"confusing":[98],"if":[99],"included":[104],"the":[106],"processing.":[107],"Our":[108],"findings":[109],"indicate":[110],"recording":[112],"native":[117],"script":[118],"help":[120],"researchers":[121],"digital":[123],"libraries":[124],"enhance":[125],"authority":[126],"control":[127],"of":[128],"continue":[133],"increase":[135],"size":[137],"bibliographic":[139],"data.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-05T06:06:40.768181","created_date":"2025-10-10T00:00:00"}
