{"id":"https://openalex.org/W4383176632","doi":"https://doi.org/10.5281/zenodo.8107513","title":"Piloting A Machine Learning Approach to Identify English-Language Fiction in the HathiTrust Digital Library","display_name":"Piloting A Machine Learning Approach to Identify English-Language Fiction in the HathiTrust Digital Library","publication_year":2023,"publication_date":"2023-06-30","ids":{"openalex":"https://openalex.org/W4383176632","doi":"https://doi.org/10.5281/zenodo.8107513"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.8107513","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8107513","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"paratext","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.8107513","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026851708","display_name":"Ryan Dubnicek","orcid":"https://orcid.org/0000-0001-7153-7030"},"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":"Dubnicek, Ryan","raw_affiliation_strings":["HathiTrust Research Center, Information Sciences, University of Illinois, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7153-7030","affiliations":[{"raw_affiliation_string":"HathiTrust Research Center, Information Sciences, University of Illinois, United States of America","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","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":"Underwood, Ted","raw_affiliation_strings":["English and Information Sciences, University of Illinois, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8960-1846","affiliations":[{"raw_affiliation_string":"English and Information Sciences, University of Illinois, United States of America","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06898256,"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":true,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9628999829292297,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9628999829292297,"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/computer-science","display_name":"Computer science","score":0.7292214035987854},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.7013502717018127},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5014481544494629},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.48004066944122314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4538775682449341},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25996673107147217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292214035987854},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.7013502717018127},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5014481544494629},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.48004066944122314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4538775682449341},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25996673107147217},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.5281/zenodo.8107513","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8107513","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.8107513","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8107513","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W3107474891","https://openalex.org/W4321496520","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W1515542156","https://openalex.org/W1992419927","https://openalex.org/W1837762017"],"abstract_inverted_index":{"In":[0],"large":[1],"digital":[2],"libraries,":[3],"such":[4],"as":[5],"the":[6,44,61],"HathiTrust,":[7],"metadata":[8,26],"is":[9],"insufficient":[10],"to":[11],"identify":[12],"items":[13],"of":[14],"interest.":[15],"Metadata":[16],"records":[17],"are":[18,30],"often":[19],"incomplete":[20],"and":[21,49,65],"challenging":[22],"for":[23,40],"fiction,":[24],"where":[25],"categories,":[27],"when":[28],"present,":[29],"too":[31],"broad.":[32],"This":[33],"project":[34],"constructs":[35],"a":[36],"machine":[37],"learning":[38],"pipeline":[39],"fiction":[41],"classification":[42],"using":[43],"HTRC":[45],"Extracted":[46],"Features":[47],"Dataset,":[48],"based":[50],"on":[51],"previous":[52],"work":[53,68],"from":[54],"Underwood":[55],"et":[56],"al.":[57],"We":[58],"will":[59],"detail":[60],"methodology,":[62],"early":[63],"results,":[64],"planned":[66],"future":[67],"in":[69],"generating":[70],"this":[71],"dataset.":[72]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
