{"id":"https://openalex.org/W6946157895","doi":"https://doi.org/10.25777/h6qt-1p64","title":"ETDSuite: A Toolkit to Mine Electronic Theses and Dissertations to Enrich Scholarly Big Data Using Natural Language Processing and Computer Vision","display_name":"ETDSuite: A Toolkit to Mine Electronic Theses and Dissertations to Enrich Scholarly Big Data Using Natural Language Processing and Computer Vision","publication_year":2025,"publication_date":"2025-02-11","ids":{"openalex":"https://openalex.org/W6946157895","doi":"https://doi.org/10.25777/h6qt-1p64"},"language":"en","primary_location":{"id":"pmh:oai:digitalcommons.odu.edu:computerscience_etds-1184","is_oa":false,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_etds/184","pdf_url":null,"source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Theses & Dissertations","raw_type":"dissertation"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.25777/h6qt-1p64","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Choudhury, Muntabir Hasan","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"]},{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]}],"countries":["GH","US"],"is_corresponding":true,"raw_author_name":"Choudhury, Muntabir Hasan","raw_affiliation_strings":["Old Dominion University"],"affiliations":[{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26189622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.13590000569820404,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.13590000569820404,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.06270000338554382,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.05139999836683273,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8636000156402588},{"id":"https://openalex.org/keywords/discoverability","display_name":"Discoverability","score":0.7638999819755554},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5299999713897705},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5152999758720398},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.4350000023841858},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.382099986076355},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.37860000133514404},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8636000156402588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669000029563904},{"id":"https://openalex.org/C2778531742","wikidata":"https://www.wikidata.org/wiki/Q17009281","display_name":"Discoverability","level":2,"score":0.7638999819755554},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5349000096321106},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5299999713897705},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.4350000023841858},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35269999504089355},{"id":"https://openalex.org/C18599908","wikidata":"https://www.wikidata.org/wiki/Q1196904","display_name":"Electronic publishing","level":3,"score":0.3328999876976013},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.3118000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2780157182","wikidata":"https://www.wikidata.org/wiki/Q11154625","display_name":"Digital Archives","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2779810430","wikidata":"https://www.wikidata.org/wiki/Q1929761","display_name":"Knowledge organization","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:digitalcommons.odu.edu:computerscience_etds-1184","is_oa":false,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_etds/184","pdf_url":null,"source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Theses & Dissertations","raw_type":"dissertation"},{"id":"doi:10.25777/h6qt-1p64","is_oa":true,"landing_page_url":"https://doi.org/10.25777/h6qt-1p64","pdf_url":null,"source":{"id":"https://openalex.org/S7407052306","display_name":"Old Dominion University","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.25777/h6qt-1p64","is_oa":true,"landing_page_url":"https://doi.org/10.25777/h6qt-1p64","pdf_url":null,"source":{"id":"https://openalex.org/S7407052306","display_name":"Old Dominion University","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[{"score":0.8319765329360962,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,243],"the":[1,21,70,77,85,99,113,130,171,177,248,267],"past":[2],"decades,":[3],"there":[4],"has":[5],"been":[6],"a":[7,81,185,209,214],"growing":[8],"interest":[9],"in":[10,116],"mining":[11,136,173],"scientific":[12,25],"documents":[13,26,62],"to":[14,140,165,189,220],"obtain":[15],"domain":[16],"knowledge":[17,114],"automatically.":[18],"One":[19,167],"of":[20,24,51,80,102,132,179,187,216,252],"understudied":[22],"types":[23],"is":[27,176,183],"Electronic":[28],"Theses":[29],"and":[30,42,69,90,95,107,111,125,149,156,223,232,239,261],"Dissertations":[31],"(ETDs),":[32],"as":[33,48],"ETDs":[34,45,103,222],"have":[35,91],"distinct":[36],"features":[37],"compared":[38],"with":[39],"conference":[40,157],"proceedings":[41],"journal":[43,154],"articles.":[44],"usually":[46,160],"serve":[47],"partial":[49],"requirements":[50],"academic":[52],"degrees":[53],"for":[54,109,153,196],"students":[55],"pursuing":[56,88],"higher":[57],"education.":[58],"They":[59],"are":[60,138],"book-length":[61],"(i.e.,":[63],"100":[64],"\u2013":[65],"400":[66],"pages":[67],"long),":[68],"topics":[71],"may":[72],"shift":[73],"across":[74],"chapters,":[75],"exhibit":[76],"significant":[78],"contribution":[79],"student\u2019s":[82],"research":[83,205],"over":[84],"entire":[86],"degree":[87],"period,":[89],"unique":[92],"metadata":[93,120,144,146,233],"schema":[94],"page":[96],"layouts.":[97],"However,":[98],"digital":[100],"libraries":[101],"lack":[104,178,186],"computational":[105],"models":[106,188,251],"services":[108],"accessing":[110],"discovering":[112],"buried":[115],"ETDs.":[117,133,166],"Moreover,":[118],"library-provided":[119],"often":[121],"exhibits":[122],"incomplete,":[123],"inconsistent,":[124],"incorrect":[126],"values,":[127],"which":[128],"harms":[129],"discoverability":[131],"Although":[134],"many":[135],"frameworks":[137,254],"developed":[139,208],"support":[141],"document":[142],"segmentation,":[143],"extraction,":[145],"quality":[147],"improvement,":[148],"parsing":[150],"reference":[151],"strings":[152],"articles":[155],"proceedings,":[158],"they":[159],"do":[161],"not":[162],"generalize":[163],"well":[164],"obstacle":[168],"that":[169],"makes":[170],"ETD":[172,194],"tasks":[174],"challenging":[175],"training":[180,197],"samples.":[181],"There":[182],"also":[184],"generate":[190],"high":[191],"fidelity":[192],"synthesized":[193],"data":[195],"deep":[198],"learning":[199,250],"based":[200,255],"models.":[201,242],"To":[202],"address":[203],"these":[204],"gaps,":[206],"we":[207,246],"toolkit":[210],"called":[211],"ETDSuite,":[212],"containing":[213],"range":[215],"machine":[217,249],"learning-based":[218],"methods":[219],"process":[221],"their":[224],"structured":[225],"components,":[226],"including":[227],"page-level-segmentation,":[228],"metadata-extraction,":[229],"citation":[230],"parsing,":[231],"enhancement":[234],"leveraging":[235],"natural":[236],"language":[237],"processing":[238],"computer":[240],"vision":[241],"this":[244],"dissertation,":[245],"describe":[247],"four":[253],"on":[256],"newly":[257],"contributed":[258],"evaluation":[259],"benchmarks":[260],"performance":[262],"while":[263],"comparing":[264],"them":[265],"against":[266],"state-of-the-art.":[268]},"counts_by_year":[],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
