{"id":"https://openalex.org/W3046687358","doi":"https://doi.org/10.1145/3383583.3398621","title":"Improving Digital Libraries' Provision of Digital Humanities Datasets: A Case Study of HTRC Literature Dataset","display_name":"Improving Digital Libraries' Provision of Digital Humanities Datasets: A Case Study of HTRC Literature Dataset","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3046687358","doi":"https://doi.org/10.1145/3383583.3398621","mag":"3046687358"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","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/A5029094200","display_name":"Yuerong Hu","orcid":"https://orcid.org/0000-0001-8375-9108"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuerong Hu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050468340","display_name":"Ming Jiang","orcid":"https://orcid.org/0000-0002-3604-166X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Jiang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006779213","display_name":"Ted Underwood","orcid":"https://orcid.org/0000-0001-8960-1846"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ted Underwood","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016957740","display_name":"J. Stephen Downie","orcid":"https://orcid.org/0000-0001-9784-5090"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Stephen Downie","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6925,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88807928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11937","display_name":"Research Data Management Practices","score":0.9668999910354614,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/digital-humanities","display_name":"Digital humanities","score":0.844190239906311},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.7125784158706665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6178556084632874},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5021607875823975},{"id":"https://openalex.org/keywords/digital-collections","display_name":"Digital collections","score":0.42687052488327026},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.406354159116745},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39474108815193176},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.3369269371032715},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32977885007858276},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.132568359375}],"concepts":[{"id":"https://openalex.org/C24351657","wikidata":"https://www.wikidata.org/wiki/Q1026962","display_name":"Digital humanities","level":2,"score":0.844190239906311},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.7125784158706665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6178556084632874},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5021607875823975},{"id":"https://openalex.org/C2988765800","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital collections","level":2,"score":0.42687052488327026},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.406354159116745},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39474108815193176},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.3369269371032715},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32977885007858276},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.132568359375},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3383583.3398621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1808906688","https://openalex.org/W1824941666","https://openalex.org/W1998899840","https://openalex.org/W2095176092","https://openalex.org/W2805358200","https://openalex.org/W2968239456","https://openalex.org/W2968567788","https://openalex.org/W3177282304"],"related_works":["https://openalex.org/W2027523974","https://openalex.org/W4255100935","https://openalex.org/W3127814564","https://openalex.org/W2483159737","https://openalex.org/W2560451689","https://openalex.org/W3012359165","https://openalex.org/W2002966468","https://openalex.org/W2729322510","https://openalex.org/W4246226487","https://openalex.org/W2912260776"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,8,39,46,63,75,81,120],"limitations":[4,113],"and":[5,71,77,86,98,110],"challenges":[6],"of":[7,17,34,48,80,96,105,122],"curated":[9,37],"datasets":[10],"provided":[11],"by":[12,38],"digital":[13,18,106,123],"libraries":[14,107],"in":[15,62,119],"support":[16],"humanities":[19,124],"(DH)":[20],"research.":[21,125],"Our":[22],"presented":[23],"work":[24],"provides":[25],"a":[26],"use":[27],"case":[28],"utilizing":[29],"an":[30],"English":[31],"literature":[32,50],"dataset":[33],"178,381":[35],"volumes":[36,53],"HathiTrust":[40,64],"Research":[41],"Center":[42],"(HTRC)":[43],"for":[44,73],"measuring":[45],"change":[47],"three":[49,89],"genres.":[51],"These":[52],"were":[54],"selected":[55],"from":[56],"over":[57],"17":[58],"million":[59],"digitized":[60],"items":[61],"Digital":[65],"Library.":[66],"We":[67,84,101],"demonstrate":[68],"our":[69],"methods":[70],"workflow":[72],"improving":[74],"representativeness":[76],"scholarly":[78],"usability":[79,118],"existing":[82],"datasets.":[83],"analyzed":[85],"effectively":[87],"overcame":[88],"common":[90],"limitations:":[91],"duplicate":[92],"volumes,":[93],"uneven":[94],"distribution":[95],"data":[97],"OCR":[99],"errors.":[100],"suggest":[102],"that":[103],"stakeholders":[104],"should":[108],"flag":[109],"address":[111],"these":[112],"to":[114],"improve":[115],"their":[116],"provisions'":[117],"context":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
