{"id":"https://openalex.org/W4205746567","doi":"https://doi.org/10.1109/bigdata52589.2021.9672058","title":"Building A Large Collection of Multi-domain Electronic Theses and Dissertations","display_name":"Building A Large Collection of Multi-domain Electronic Theses and Dissertations","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205746567","doi":"https://doi.org/10.1109/bigdata52589.2021.9672058"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9672058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672058","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vtechworks.lib.vt.edu/bitstreams/09d1d81d-5301-44d5-b5df-ed4e93f74b56/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110961247","display_name":"Sami Uddin","orcid":null},"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":"Sami Uddin","raw_affiliation_strings":["Computer Science, Old Dominion University, Norfolk, VA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science, Old Dominion University, Norfolk, VA, United States","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085592027","display_name":"Bipasha Banerjee","orcid":"https://orcid.org/0000-0003-4472-1902"},"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":"Bipasha Banerjee","raw_affiliation_strings":["Computer Science, Virginia Polytechnic Institute and State University, VA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Polytechnic Institute and State University, VA, United States","institution_ids":["https://openalex.org/I859038795"]}]},{"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":["Computer Science, Old Dominion University, Norfolk, VA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science, Old Dominion University, 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, VA, United States"],"affiliations":[{"raw_affiliation_string":"University Libraries, Virginia Polytechnic Institute and State University, 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":["Computer Science, Virginia Polytechnic Institute and State University, VA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Polytechnic Institute and State University, VA, United States","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5110961247"],"corresponding_institution_ids":["https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":1.7096,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85807292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6043","last_page":"6045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9417999982833862,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11937","display_name":"Research Data Management Practices","score":0.9417999982833862,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9275000095367432,"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":0.9182000160217285,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6295626759529114},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46929794549942017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295626759529114},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46929794549942017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9672058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672058","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/117428","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/117428","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/09d1d81d-5301-44d5-b5df-ed4e93f74b56/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/117428","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/117428","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/09d1d81d-5301-44d5-b5df-ed4e93f74b56/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4205746567.pdf","grobid_xml":"https://content.openalex.org/works/W4205746567.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2051891290","https://openalex.org/W2570427954","https://openalex.org/W2912067075","https://openalex.org/W3015453090","https://openalex.org/W3176028514","https://openalex.org/W3176349801","https://openalex.org/W4238044281"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,52,100],"report":[4],"our":[5,105],"progress":[6],"on":[7],"building":[8,111],"a":[9,42],"collection":[10],"containing":[11],"over":[12],"450k":[13],"Electronic":[14],"Theses":[15],"and":[16,21,35,39,63,74,117,126],"Dissertations":[17],"(ETDs),":[18],"including":[19],"full-text":[20],"metadata.":[22],"Our":[23],"goal":[24],"is":[25],"to":[26,40,83,86],"close":[27],"the":[28,47,79,88,91,97,119],"gap":[29],"of":[30,65,90],"accessibility":[31],"between":[32],"long":[33],"text":[34,37],"short":[36],"documents,":[38],"create":[41],"new":[43],"research":[44,125],"opportunity":[45],"for":[46,110,124],"scholarly":[48],"community.":[49],"For":[50],"that,":[51],"developed":[53],"an":[54],"ETD":[55],"Ingestion":[56],"Framework":[57],"(EIF)":[58],"that":[59,81,99,118],"automatically":[60],"harvests":[61],"metadata":[62],"PDFs":[64],"ETDs":[66],"from":[67,114],"university":[68,115],"libraries.":[69],"We":[70,94,103],"faced":[71],"multiple":[72],"challenges":[73],"learned":[75],"many":[76],"lessons":[77],"during":[78],"process,":[80],"led":[82],"proposed":[84],"solutions":[85],"overcome/mitigate":[87],"limitations":[89],"current":[92],"data.":[93],"also":[95],"described":[96],"data":[98,120],"have":[101],"collected.":[102],"hope":[104],"methods":[106],"will":[107],"be":[108,122],"useful":[109],"similar":[112],"collections":[113],"libraries":[116],"can":[121],"used":[123],"education.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}