{"id":"https://openalex.org/W4398579273","doi":"https://doi.org/10.7910/dvn/avnzr6","title":"Replication Data for: An Improved Method of Automated Nonparametric Content Analysis for Social Science","display_name":"Replication Data for: An Improved Method of Automated Nonparametric Content Analysis for Social Science","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4398579273","doi":"https://doi.org/10.7910/dvn/avnzr6"},"language":"en","primary_location":{"id":"doi:10.7910/dvn/avnzr6","doi":"https://doi.org/10.7910/dvn/avnzr6","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/avnzr6","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7910/dvn/avnzr6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026867670","display_name":"Connor Jerzak","orcid":"https://orcid.org/0000-0003-1914-8905","observed_orcids":["https://orcid.org/0000-0003-1914-8905"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerzak, Connor","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421071","display_name":"Gary King","orcid":"https://orcid.org/0000-0002-5327-7631","observed_orcids":["https://orcid.org/0000-0002-5327-7631"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"King, Gary","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046865751","display_name":"Anton Strezhnev","orcid":"https://orcid.org/0000-0001-6847-8340","observed_orcids":["https://orcid.org/0000-0001-6847-8340"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Strezhnev, Anton","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9945999979972839,"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":0.9945999979972839,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0052999998442828655,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/document-classification","display_name":"document classification","score":0.5040000081062317},{"id":"https://openalex.org/keywords/proportion-estimation","display_name":"proportion estimation","score":0.628000020980835},{"id":"https://openalex.org/keywords/direct-estimation","display_name":"direct estimation","score":0.5410000085830688},{"id":"https://openalex.org/keywords/textual-features","display_name":"text features","score":0.6449999809265137},{"id":"https://openalex.org/keywords/language-change","display_name":"language change","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.8387148380279541},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.644622802734375},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5971057415008545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5909765362739563},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.47256606817245483},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4039066433906555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3389050364494324},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22771459817886353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16247200965881348},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.13052630424499512},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.09543094038963318},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7910/dvn/avnzr6","doi":"https://doi.org/10.7910/dvn/avnzr6","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/avnzr6","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.7910/dvn/avnzr6","doi":"https://doi.org/10.7910/dvn/avnzr6","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/avnzr6","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6945215876","https://openalex.org/W4398448429","https://openalex.org/W2171060319","https://openalex.org/W2121781523","https://openalex.org/W2791375294","https://openalex.org/W1553213283","https://openalex.org/W7095558884","https://openalex.org/W3190803861","https://openalex.org/W2032158738","https://openalex.org/W97193787"],"abstract_inverted_index":{"Some":[0],"scholars":[1],"build":[2],"models":[3],"to":[4,16],"classify":[5],"documents":[6,27,66],"into":[7],"chosen":[8],"categories.":[9,94],"Others,":[10],"especially":[11],"social":[12],"scientists":[13],"who":[14],"tend":[15],"focus":[17],"on":[18],"population":[19],"characteristics,":[20],"instead":[21],"usually":[22],"estimate":[23],"the":[24,59,63,79,120],"proportion":[25],"of":[26,41,65,81,116,133],"in":[28,58,129],"each":[29],"category":[30],"--":[31],"using":[32],"either":[33],"parametric":[34],"\"classify-and-count\"":[35],"methods":[36,48],"or":[37,54,89],"\"direct\"":[38],"nonparametric":[39],"estimation":[40,71,100],"proportions":[42,60],"without":[43,102],"individual":[44],"classification.":[45],"Unfortunately,":[46],"classify-and-count":[47],"can":[49,76],"be":[50],"highly":[51],"model":[52],"dependent":[53],"generate":[55],"more":[56],"bias":[57],"even":[61],"as":[62],"percent":[64],"correctly":[67],"classified":[68],"increases.":[69],"Direct":[70],"avoids":[72],"these":[73,103],"problems,":[74],"but":[75],"suffer":[77],"when":[78],"meaning":[80],"language":[82],"changes":[83],"between":[84],"training":[85],"and":[86,107],"test":[87],"sets":[88],"is":[90],"too":[91],"similar":[92],"across":[93],"We":[95,137],"develop":[96],"an":[97],"improved":[98],"direct":[99],"approach":[101,125],"issues":[104],"by":[105],"including":[106],"optimizing":[108],"continuous":[109],"text":[110],"features,":[111],"along":[112],"with":[113],"a":[114,130],"form":[115],"matching":[117],"adapted":[118],"from":[119],"causal":[121],"inference":[122],"literature.":[123],"Our":[124],"substantially":[126],"improves":[127],"performance":[128],"diverse":[131],"collection":[132],"73":[134],"data":[135],"sets.":[136],"also":[138],"offer":[139],"easy-to-use":[140],"software":[141],"that":[142],"implements":[143],"all":[144],"ideas":[145],"discussed":[146],"herein.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2024-05-24T00:00:00"}