{"id":"https://openalex.org/W4406459893","doi":"https://doi.org/10.1109/bigdata62323.2024.10825738","title":"Toward Automatically Improving Metadata Quality of Electronic Theses and Dissertations at Scale","display_name":"Toward Automatically Improving Metadata Quality of Electronic Theses and Dissertations at Scale","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459893","doi":"https://doi.org/10.1109/bigdata62323.2024.10825738"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-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/A5054690853","display_name":"Lamia Salsabil","orcid":"https://orcid.org/0000-0002-6162-2896"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lamia Salsabil","raw_affiliation_strings":["Old Dominion University,Computer Science,Norfolk,VA,United States"],"affiliations":[{"raw_affiliation_string":"Old Dominion University,Computer Science,Norfolk,VA,United States","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Old Dominion University,Computer Science,Norfolk,VA,United States"],"affiliations":[{"raw_affiliation_string":"Old Dominion University,Computer Science,Norfolk,VA,United States","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062743697","display_name":"William A. Ingram","orcid":"https://orcid.org/0000-0002-8307-8844"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William A. Ingram","raw_affiliation_strings":["University Libraries, Virginia Polytechnic Institute and State University,Blacksburg,VA,United States"],"affiliations":[{"raw_affiliation_string":"University Libraries, Virginia Polytechnic Institute and State University,Blacksburg,VA,United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049148461","display_name":"Edward A. Fox","orcid":"https://orcid.org/0000-0003-1447-6870"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward A. Fox","raw_affiliation_strings":["Virginia Polytechnic Institute and State University,Computer Science,Blacksburg,VA,United States"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University,Computer Science,Blacksburg,VA,United States","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054690853"],"corresponding_institution_ids":["https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23770653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8825","last_page":"8827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9961000084877014,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9961000084877014,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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":0.9807000160217285,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8903042078018188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7645885944366455},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6872162818908691},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6480244398117065},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49636703729629517},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3692095875740051},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3317917585372925},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.049271583557128906}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8903042078018188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645885944366455},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6872162818908691},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6480244398117065},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49636703729629517},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3692095875740051},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3317917585372925},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.049271583557128906},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W791527587","https://openalex.org/W1983503745","https://openalex.org/W2910299552","https://openalex.org/W3176349801","https://openalex.org/W3177049011","https://openalex.org/W4200362276","https://openalex.org/W4290988679","https://openalex.org/W4387316212","https://openalex.org/W6752788575"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W2361979572"],"abstract_inverted_index":{"Metadata":[0],"is":[1],"crucial":[2],"for":[3,127],"the":[4,30,68,83,117,124,128],"accessibility,":[5],"interoperability,":[6],"and":[7,17,32,43,59,89,123],"long-term":[8],"usability":[9],"of":[10,34,41,70,101],"digital":[11],"objects":[12],"such":[13],"as":[14],"Electronic":[15],"Theses":[16],"Dissertations":[18],"(ETDs).":[19],"In":[20],"large-scale":[21],"academic":[22],"repositories,":[23],"poor":[24],"metadata":[25,46,77,87,110,126],"quality":[26],"can":[27],"significantly":[28],"impede":[29],"discovery":[31],"use":[33],"resources.":[35],"This":[36],"study":[37],"addresses":[38],"persistent":[39],"issues":[40],"incomplete":[42],"inconsistent":[44],"ETD":[45,76],"collected":[47],"from":[48],"U.S.":[49,103],"university":[50],"libraries.":[51],"However,":[52],"directly":[53],"applying":[54],"machine":[55],"learning-based":[56],"error":[57],"detection":[58],"correction":[60],"models":[61],"may":[62],"introduce":[63],"unwanted":[64],"errors":[65],"due":[66],"to":[67,98],"imperfection":[69],"these":[71],"models.":[72],"We":[73],"propose":[74],"an":[75],"improvement":[78],"system":[79,95],"(ETDMIS)":[80],"that":[81],"mitigates":[82],"problem":[84],"by":[85,115],"integrating":[86],"validation":[88],"a":[90,99],"version":[91],"control":[92],"mechanism.":[93],"Our":[94],"was":[96,113],"applied":[97],"dataset":[100,119],"100,000":[102,129],"ETDs,":[104],"resulting":[105],"in":[106,109],"substantial":[107],"improvements":[108],"quality.":[111],"Scalability":[112],"demonstrated":[114],"processing":[116],"entire":[118],"efficiently.":[120],"The":[121],"original":[122],"enhanced":[125],"ETDs":[130],"are":[131],"publicly":[132],"accessible":[133],"at":[134],"https://github.com/lamps-lab/ETDMiner/tree/master/Meta100K.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}