{"id":"https://openalex.org/W4210859164","doi":"https://doi.org/10.1109/access.2022.3149897","title":"Misclassification Bias in Computational Social Science: A Simulation Approach for Assessing the Impact of Classification Errors on Social Indicators Research","display_name":"Misclassification Bias in Computational Social Science: A Simulation Approach for Assessing the Impact of Classification Errors on Social Indicators Research","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4210859164","doi":"https://doi.org/10.1109/access.2022.3149897"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3149897","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3149897","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09706439.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09706439.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048780674","display_name":"Sergey Smetanin","orcid":"https://orcid.org/0000-0001-6373-3410"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Smetanin","raw_affiliation_strings":["Department of Business Informatics, Graduate School of Business, National Research University Higher School of Economics, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0001-6373-3410","affiliations":[{"raw_affiliation_string":"Department of Business Informatics, Graduate School of Business, National Research University Higher School of Economics, Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068776818","display_name":"Mikhail Komarov","orcid":"https://orcid.org/0000-0001-7075-0016"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Mikhail Komarov","raw_affiliation_strings":["Department of Business Informatics, Graduate School of Business, National Research University Higher School of Economics, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0001-7075-0016","affiliations":[{"raw_affiliation_string":"Department of Business Informatics, Graduate School of Business, National Research University Higher School of Economics, Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118501908"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":5.4385,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9628821,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"18886","last_page":"18898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.9907000064849854,"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"}},{"id":"https://openalex.org/T13051","display_name":"Qualitative Comparative Analysis Research","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/computer-science","display_name":"Computer science","score":0.709526538848877},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5847408771514893},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5329523682594299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5252594351768494},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.50788813829422},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48219504952430725},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46742624044418335},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4145854115486145},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3203643560409546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.235455721616745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709526538848877},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5847408771514893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5329523682594299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5252594351768494},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.50788813829422},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48219504952430725},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46742624044418335},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4145854115486145},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3203643560409546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.235455721616745},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3149897","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3149897","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09706439.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d3fc775f847b43f186dc401a633616de","is_oa":true,"landing_page_url":"https://doaj.org/article/d3fc775f847b43f186dc401a633616de","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":"IEEE Access, Vol 10, Pp 18886-18898 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3149897","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3149897","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09706439.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4210859164.pdf","grobid_xml":"https://content.openalex.org/works/W4210859164.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W14192288","https://openalex.org/W184906668","https://openalex.org/W241835013","https://openalex.org/W1584252592","https://openalex.org/W1795944322","https://openalex.org/W1840284311","https://openalex.org/W1974053281","https://openalex.org/W1981485901","https://openalex.org/W1983993360","https://openalex.org/W2009034184","https://openalex.org/W2015363484","https://openalex.org/W2038286139","https://openalex.org/W2039297951","https://openalex.org/W2086211531","https://openalex.org/W2109474247","https://openalex.org/W2121712502","https://openalex.org/W2126052291","https://openalex.org/W2144409155","https://openalex.org/W2171060319","https://openalex.org/W2171326738","https://openalex.org/W2267923631","https://openalex.org/W2320012450","https://openalex.org/W2342845725","https://openalex.org/W2524454060","https://openalex.org/W2525742502","https://openalex.org/W2586816396","https://openalex.org/W2737838117","https://openalex.org/W2757560572","https://openalex.org/W2775760745","https://openalex.org/W2791375294","https://openalex.org/W2804974507","https://openalex.org/W2807177388","https://openalex.org/W2899115790","https://openalex.org/W2909157294","https://openalex.org/W2909324897","https://openalex.org/W2915469157","https://openalex.org/W2922073769","https://openalex.org/W2969250152","https://openalex.org/W2982280746","https://openalex.org/W3007157104","https://openalex.org/W3034576047","https://openalex.org/W3035056367","https://openalex.org/W3039901811","https://openalex.org/W3044246577","https://openalex.org/W3105109036","https://openalex.org/W3116364167","https://openalex.org/W3121606938","https://openalex.org/W3125131374","https://openalex.org/W3134427152","https://openalex.org/W3149313574","https://openalex.org/W3160617790","https://openalex.org/W3176381893","https://openalex.org/W4205930252","https://openalex.org/W4231619706","https://openalex.org/W4235535825","https://openalex.org/W4242999626","https://openalex.org/W4248083651","https://openalex.org/W6609274782","https://openalex.org/W6631984995","https://openalex.org/W6733058199","https://openalex.org/W6753356487"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W2364238915","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W2096492911","https://openalex.org/W4205958290","https://openalex.org/W4384212932","https://openalex.org/W2562018983","https://openalex.org/W4390590544"],"abstract_inverted_index":{"A":[0],"growing":[1],"body":[2],"of":[3,9,22,39,43,57,66,80,96,110,126,133,139,175,185,201,208,233,237,247],"literature":[4],"has":[5],"examined":[6],"the":[7,19,29,37,40,55,58,94,108,124,130,137,173,179,199,215,234,240,245,248,252],"potential":[8],"machine":[10],"learning":[11],"algorithms":[12],"in":[13,88,155,183],"constructing":[14],"social":[15,60,117,181,223],"indicators":[16,182,195],"based":[17,197,243],"on":[18,77,114,178,194,198,244],"automatic":[20,134],"classification":[21,30,135,218,249],"digital":[23],"traces.":[24],"However,":[25],"as":[26,28,152],"long":[27],"algorithms\u2019":[31],"predictions":[32],"are":[33,83],"not":[34,146],"completely":[35],"error-free,":[36],"estimate":[38],"relative":[41],"occurrence":[42],"a":[44,63,78,102,115,140,168,221],"particular":[45,222],"class":[46],"may":[47],"be":[48,86,144],"affected":[49],"by":[50],"misclassification":[51,70,111,176],"bias,":[52],"thereby":[53],"affecting":[54],"value":[56],"calculated":[59,180,196,242],"indicator.":[61,255],"Although":[62],"significant":[64],"amount":[65],"studies":[67],"have":[68],"investigated":[69],"bias":[71,177],"correction":[72],"techniques,":[73],"they":[74],"commonly":[75],"rely":[76],"set":[79],"assumptions":[81],"that":[82],"likely":[84],"to":[85,107,123],"violated":[87],"practice,":[89],"which":[90],"calls":[91],"into":[92],"question":[93],"effectiveness":[95],"these":[97],"methods.":[98],"Thus,":[99],"there":[100],"is":[101],"knowledge":[103],"gap":[104],"with":[105],"respect":[106],"assessment":[109,232],"bias\u2019s":[112],"impact":[113,174],"specific":[116],"indicator":[118,142,241],"formula":[119],"without":[120],"strict":[121],"reference":[122],"number":[125,207],"classes.":[127,209],"Moreover,":[128,228],"given":[129],"erroneous":[131],"nature":[132],"algorithms,":[136],"quality":[138,150],"predicted":[141],"can":[143,204],"assessed":[145],"only":[147],"using":[148,160],"regression":[149,186],"metrics,":[151],"was":[153],"done":[154],"existing":[156],"literature,":[157],"but":[158],"also":[159],"correlation":[161,188,238],"metrics.":[162,189],"In":[163],"this":[164],"paper,":[165],"we":[166],"propose":[167],"simulation":[169],"approach":[170,192,212],"for":[171,220,231],"assessing":[172],"terms":[184],"and":[187,203,225,251],"The":[190,210],"proposed":[191,211],"focuses":[193],"distribution":[200],"classes":[202],"process":[205],"any":[206],"allows":[213,230],"selecting":[214],"most":[216],"appropriate":[217],"model":[219],"indicator,":[224],"vice":[226],"versa.":[227],"it":[229],"optimistic":[235],"level":[236],"between":[239],"results":[246],"algorithm":[250],"true":[253],"underlying":[254]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}