{"id":"https://openalex.org/W2042641525","doi":"https://doi.org/10.1145/2494266.2494312","title":"Near duplicate detection in an academic digital library","display_name":"Near duplicate detection in an academic digital library","publication_year":2013,"publication_date":"2013-09-03","ids":{"openalex":"https://openalex.org/W2042641525","doi":"https://doi.org/10.1145/2494266.2494312","mag":"2042641525"},"language":"en","primary_location":{"id":"doi:10.1145/2494266.2494312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM symposium on Document engineering","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/A5108439761","display_name":"Kyle Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle Williams","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108439761"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":10.031,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.97686012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9954000115394592,"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/T11719","display_name":"Data Quality and Management","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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":0.8229153156280518},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.7199658155441284},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6913880705833435},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.605225682258606},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5651930570602417},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4705921411514282},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4411110281944275},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28443586826324463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1562182605266571},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14986485242843628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229153156280518},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.7199658155441284},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6913880705833435},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.605225682258606},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5651930570602417},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4705921411514282},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4411110281944275},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28443586826324463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1562182605266571},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14986485242843628},{"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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2494266.2494312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.403.7316","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.403.7316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.personal.psu.edu/kiw5209/papers/2013/williams_doceng2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2012833704","https://openalex.org/W2053107662","https://openalex.org/W2067432306","https://openalex.org/W2085922539","https://openalex.org/W2097156061","https://openalex.org/W2145349611","https://openalex.org/W2152565070"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W2094012830","https://openalex.org/W187246281","https://openalex.org/W3151146928"],"abstract_inverted_index":{"The":[0,98,113],"detection":[1,51,68],"and":[2,23,25,44,70,74,79,104,109],"potential":[3],"removal":[4],"of":[5,12,41,47,91,121],"duplicates":[6,93],"is":[7],"desirable":[8],"for":[9,20,53,83,106],"a":[10,118],"number":[11],"reasons,":[13],"such":[14],"as":[15],"to":[16,26,76],"reduce":[17],"the":[18,39,48,59,66,84,89,107,125],"need":[19],"unnecessary":[21],"storage":[22],"computation,":[24],"provide":[27],"users":[28],"with":[29],"uncluttered":[30],"search":[31],"results.":[32],"This":[33],"paper":[34],"describes":[35],"an":[36],"investigation":[37],"into":[38],"application":[40,75],"scalable":[42],"simhash":[43,108],"shingle":[45],"state":[46],"art":[49],"duplicate":[50,56,67,122],"algorithms":[52],"detecting":[54],"near":[55,92],"documents":[57,78],"in":[58],"CiteSeerX":[60],"digital":[61],"library.":[62],"We":[63,86],"empirically":[64],"explored":[65],"methods":[69,111],"evaluated":[71],"their":[72],"performance":[73],"academic":[77],"identified":[80,94,117],"good":[81],"parameters":[82],"algorithms.":[85],"also":[87,116],"analyzed":[88],"types":[90,123],"by":[95],"each":[96],"algorithm.":[97],"highest":[99],"F-scores":[100],"achieved":[101],"were":[102],"0.91":[103],"0.99":[105],"shingle-based":[110,114],"respectively.":[112],"method":[115],"larger":[119],"variety":[120],"than":[124],"simhash-based":[126],"method.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}