{"id":"https://openalex.org/W1567330154","doi":"https://doi.org/10.1002/meet.2014.14505101098","title":"Author gender metadata augmentation of hathitrust digital library","display_name":"Author gender metadata augmentation of hathitrust digital library","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1567330154","doi":"https://doi.org/10.1002/meet.2014.14505101098","mag":"1567330154"},"language":"en","primary_location":{"id":"doi:10.1002/meet.2014.14505101098","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101098","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101098","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101098","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101552848","display_name":"Zong Peng","orcid":"https://orcid.org/0000-0001-5428-9039"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zong Peng","raw_affiliation_strings":["Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408"],"affiliations":[{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382073","display_name":"Miao Chen","orcid":"https://orcid.org/0000-0001-5165-9823"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Miao Chen","raw_affiliation_strings":["Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408"],"affiliations":[{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053950143","display_name":"Stacy Kowalczyk","orcid":"https://orcid.org/0000-0002-1299-1425"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stacy Kowalczyk","raw_affiliation_strings":["Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408"],"affiliations":[{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060672408","display_name":"Beth Plale","orcid":"https://orcid.org/0000-0003-2164-8132"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Beth Plale","raw_affiliation_strings":["Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408"],"affiliations":[{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute  2079 E 10<sup>th</sup> St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Data to Insight Center Indiana University Pervasive Technology Institute 2079 E 10th St Bloomington IN 47408","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053950143","https://openalex.org/A5060672408","https://openalex.org/A5100382073","https://openalex.org/A5101552848"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71869017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"51","issue":"1","first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.9959999918937683,"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/metadata","display_name":"Metadata","score":0.9624863862991333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7133103013038635},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6864429116249084},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6710035800933838},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.614607036113739},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5869013667106628},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5397833585739136},{"id":"https://openalex.org/keywords/public-domain","display_name":"Public domain","score":0.5366672277450562},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5048292279243469},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4772348701953888},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43397656083106995},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.3230350613594055},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.116324782371521},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06980165839195251}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9624863862991333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133103013038635},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6864429116249084},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6710035800933838},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.614607036113739},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5869013667106628},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5397833585739136},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.5366672277450562},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5048292279243469},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4772348701953888},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43397656083106995},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.3230350613594055},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.116324782371521},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06980165839195251},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/meet.2014.14505101098","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101098","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101098","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1002/meet.2014.14505101098","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101098","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101098","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1567330154.pdf","grobid_xml":"https://content.openalex.org/works/W1567330154.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W197637193","https://openalex.org/W1715117582","https://openalex.org/W2019884017","https://openalex.org/W2032793012","https://openalex.org/W2051888428","https://openalex.org/W2076915037","https://openalex.org/W2081666882","https://openalex.org/W2096703131","https://openalex.org/W2139875525","https://openalex.org/W2159852928","https://openalex.org/W2169097200","https://openalex.org/W2947745569","https://openalex.org/W6762949126"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W1987401411","https://openalex.org/W2481644306","https://openalex.org/W2969781498"],"abstract_inverted_index":{"ABSTRACT":[0],"Bibliographic":[1],"metadata":[2,21,67],"is":[3],"essential":[4],"for":[5],"digital":[6,26,43,72,77],"library":[7,27],"resource":[8],"description.":[9],"Especially":[10],"as":[11],"the":[12,48,66,74,82,87,92,105,118,120,125,138,141,153],"size":[13],"and":[14,30,136,147],"number":[15],"of":[16,25,50,53,69,84,86,91,117,122,140],"bibliographic":[17],"entities":[18],"grows,":[19],"high\u2010quality":[20],"enables":[22],"richer":[23],"forms":[24],"access,":[28],"search,":[29],"use.":[31],"Metadata":[32],"records":[33],"can":[34],"be":[35],"enriched":[36],"through":[37,104],"automated":[38],"techniques.":[39],"For":[40],"example,":[41],"a":[42,51,70,99],"humanities":[44],"scholar":[45],"might":[46],"use":[47],"gender":[49,83,121],"set":[52],"authors":[54,85,123],"during":[55],"their":[56],"literature":[57],"analysis.":[58],"In":[59],"this":[60],"study,":[61,111],"we":[62],"undertook":[63],"to":[64,98,144,151],"enrich":[65],"description":[68],"large\u2010scale":[71],"library,":[73,78],"HathiTrust":[75,106],"(HT)":[76],"specifically":[79],"by":[80],"determining":[81],"public":[88,127],"domain":[89,128],"portion":[90],"collection.":[93],"The":[94],"results":[95],"are":[96],"stored":[97],"separate":[100],"Solr":[101],"index":[102],"accessible":[103],"Research":[107],"Center":[108],"services.":[109],"This":[110],"which":[112],"successfully":[113],"resolved":[114],"in":[115,124,134,148],"78.9%":[116],"cases":[119],"HT":[126],"corpus,":[129],"suggests":[130],"future":[131],"research":[132],"directions":[133],"capturing":[135],"representing":[137],"provenance":[139],"contributing":[142],"sources":[143],"enhance":[145],"trust,":[146],"machine":[149],"learning":[150],"resolve":[152],"remaining":[154],"names.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
