{"id":"https://openalex.org/W3046244497","doi":"https://doi.org/10.1145/3383583.3398586","title":"Challenges and Solutions of Identifying Similarities and Duplication in Digital Libraries","display_name":"Challenges and Solutions of Identifying Similarities and Duplication in Digital Libraries","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3046244497","doi":"https://doi.org/10.1145/3383583.3398586","mag":"3046244497"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398586","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/A5088531349","display_name":"Maggie Ryan","orcid":null},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maggie Ryan","raw_affiliation_strings":["University of Denver, Denver, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Denver, Denver, CO, USA","institution_ids":["https://openalex.org/I131651094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088978867","display_name":"Ruiwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiwen (Rita) Zhang","raw_affiliation_strings":["University of Denver, Denver, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Denver, Denver, CO, USA","institution_ids":["https://openalex.org/I131651094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068216330","display_name":"Matthew Durward","orcid":"https://orcid.org/0000-0002-1131-8132"},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Durward","raw_affiliation_strings":["University of Denver, Denver, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Denver, Denver, CO, USA","institution_ids":["https://openalex.org/I131651094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091234228","display_name":"Krystyna K. Matusiak","orcid":"https://orcid.org/0000-0003-2713-866X"},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krystyna Matusiak","raw_affiliation_strings":["University of Denver, Denver, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Denver, Denver, CO, USA","institution_ids":["https://openalex.org/I131651094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001038669","display_name":"Peter Organisciak","orcid":"https://orcid.org/0000-0002-9058-2280"},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Organisciak","raw_affiliation_strings":["University of Denver, Denver, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Denver, Denver, CO, USA","institution_ids":["https://openalex.org/I131651094"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1354,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55321658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"507","last_page":"508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9919999837875366,"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/T10028","display_name":"Topic Modeling","score":0.9902999997138977,"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/metadata","display_name":"Metadata","score":0.922404944896698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8029639720916748},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6842767596244812},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6739205121994019},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6088336706161499},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.587096095085144},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4687231779098511},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4235912263393402},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.41106700897216797},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40928488969802856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1532980501651764},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09184607863426208},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07612690329551697}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.922404944896698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029639720916748},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6842767596244812},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6739205121994019},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6088336706161499},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.587096095085144},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4687231779098511},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4235912263393402},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.41106700897216797},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40928488969802856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1532980501651764},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09184607863426208},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07612690329551697},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3383583.3398586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398586","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2037076772","https://openalex.org/W2913604083"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2768810474","https://openalex.org/W1987401411"],"abstract_inverted_index":{"Large-scale":[0],"digital":[1,58],"libraries":[2],"such":[3],"as":[4,126],"the":[5,91,102,106,122,127,143,146,153,156],"HathiTrust,":[6],"with":[7],"access":[8,23],"to":[9,32,64,72,89,120,141,152],"over":[10],"17":[11],"million":[12],"texts,":[13],"include":[14],"duplicative":[15],"texts":[16],"and":[17,24,40,68],"metadata":[18,119],"inconsistencies":[19],"that":[20],"impede":[21],"information":[22],"retrieval.":[25],"At":[26],"this":[27,85,138],"scale,":[28],"it":[29],"is":[30,140,150],"untenable":[31],"manually":[33],"evaluate":[34],"each":[35],"text.":[36,157],"The":[37,135],"SaDDL":[38],"(Similarities":[39],"Duplication":[41],"in":[42,70],"Digital":[43],"Libraries)":[44],"project":[45],"has":[46],"been":[47],"developing":[48],"content-based":[49],"methods":[50],"for":[51],"identifying":[52],"similar":[53],"text":[54],"relationships":[55,109],"within":[56],"a":[57,76,96],"library.":[59],"This":[60,99],"framework":[61],"allows":[62,87],"us":[63,88],"quantify":[65],"words,":[66],"themes,":[67],"concepts":[69],"order":[71],"identify":[73,90],"similarity":[74],"on":[75],"massive":[77],"scale":[78],"currently":[79],"unobtainable":[80],"by":[81],"human":[82],"effort.":[83],"Secondly,":[84],"method":[86],"most":[92,123,128],"representative":[93,124],"scan":[94],"of":[95,104,133,155],"target":[97],"work.":[98,134],"poster":[100],"presents":[101],"way":[103],"reconstructing":[105],"same":[107],"work":[108],"deriving":[110],"from":[111],"content":[112,147],"comparison":[113],"directly,":[114],"rather":[115],"than":[116],"matched":[117],"superficial":[118],"obtain":[121],"copy---defined":[125],"complete,":[129],"correct,":[130],"cleanest":[131],"expression":[132],"philosophy":[136],"behind":[137],"approach":[139],"study":[142],"collection":[144],"emphasizing":[145],"itself,":[148],"which":[149],"closer":[151],"essence":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
