{"id":"https://openalex.org/W1923382164","doi":"https://doi.org/10.17562/pb-45-3","title":"String Distances for Near-duplicate Detection","display_name":"String Distances for Near-duplicate Detection","publication_year":2012,"publication_date":"2012-06-30","ids":{"openalex":"https://openalex.org/W1923382164","doi":"https://doi.org/10.17562/pb-45-3","mag":"1923382164"},"language":"en","primary_location":{"id":"doi:10.17562/pb-45-3","is_oa":true,"landing_page_url":"https://doi.org/10.17562/pb-45-3","pdf_url":"https://www.polibits.cidetec.ipn.mx/ojs/index.php/polibits/article/view/45-3/1743","source":{"id":"https://openalex.org/S4210186437","display_name":"Polibits","issn_l":"1870-9044","issn":["1870-9044","2395-8618"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Polibits","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.polibits.cidetec.ipn.mx/ojs/index.php/polibits/article/view/45-3/1743","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051493770","display_name":"Iulia D\u0103n\u0103il\u0103","orcid":null},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Iulia D\u0103n\u0103il\u0103","raw_affiliation_strings":["University of Bucharest, Faculty of Mathematics and Computer Science, Bucarest, Rumania"],"affiliations":[{"raw_affiliation_string":"University of Bucharest, Faculty of Mathematics and Computer Science, Bucarest, Rumania","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057738797","display_name":"Liviu P. Dinu","orcid":"https://orcid.org/0000-0002-7559-6756"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Liviu P. Dinu","raw_affiliation_strings":["University of Bucharest, Faculty of Mathematics and Computer Science, Bucarest, Rumania"],"affiliations":[{"raw_affiliation_string":"University of Bucharest, Faculty of Mathematics and Computer Science, Bucarest, Rumania","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064085103","display_name":"Vlad Niculae","orcid":null},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Vlad Niculae","raw_affiliation_strings":["University of Bucharest, Faculty of Mathematics and Computer Science, Bucarest, Rumania"],"affiliations":[{"raw_affiliation_string":"University of Bucharest, Faculty of Mathematics and Computer Science, Bucarest, Rumania","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022951153","display_name":"Octavia-Maria \u015eulea","orcid":null},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Octavia-Maria \u0218ulea","raw_affiliation_strings":["University of Bucharest, Faculty of Foreign Languages and Literatures, Bucarest, Rumania"],"affiliations":[{"raw_affiliation_string":"University of Bucharest, Faculty of Foreign Languages and Literatures, Bucarest, Rumania","institution_ids":["https://openalex.org/I141595442"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051493770"],"corresponding_institution_ids":["https://openalex.org/I141595442"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10797546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"45","issue":null,"first_page":"21","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9975000023841858,"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/string","display_name":"String (physics)","score":0.6088802218437195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5590688586235046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37920013070106506},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3771924674510956},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.33584314584732056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29691082239151},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19747602939605713},{"id":"https://openalex.org/keywords/theoretical-physics","display_name":"Theoretical physics","score":0.0926922857761383}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6088802218437195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5590688586235046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37920013070106506},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3771924674510956},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.33584314584732056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29691082239151},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19747602939605713},{"id":"https://openalex.org/C33332235","wikidata":"https://www.wikidata.org/wiki/Q18362","display_name":"Theoretical physics","level":1,"score":0.0926922857761383}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.17562/pb-45-3","is_oa":true,"landing_page_url":"https://doi.org/10.17562/pb-45-3","pdf_url":"https://www.polibits.cidetec.ipn.mx/ojs/index.php/polibits/article/view/45-3/1743","source":{"id":"https://openalex.org/S4210186437","display_name":"Polibits","issn_l":"1870-9044","issn":["1870-9044","2395-8618"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Polibits","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.401.5232","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.401.5232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://polibits.gelbukh.com/2012_45/String Distances for Near-duplicate Detection.pdf","raw_type":"text"},{"id":"pmh:oai:redalyc.org:402640459004","is_oa":false,"landing_page_url":"https://www.redalyc.org/articulo.oa?id=402640459004","pdf_url":null,"source":{"id":"https://openalex.org/S4377196100","display_name":"Redalyc (Universidad Aut\u00f3noma del Estado de M\u00e9xico)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I179647637","host_organization_name":"Universidad Aut\u00f3noma del Estado de M\u00e9xico","host_organization_lineage":["https://openalex.org/I179647637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Polibits (M\u00e9xico) Vol.45","raw_type":"art\u00edculo cient\u00edfico"}],"best_oa_location":{"id":"doi:10.17562/pb-45-3","is_oa":true,"landing_page_url":"https://doi.org/10.17562/pb-45-3","pdf_url":"https://www.polibits.cidetec.ipn.mx/ojs/index.php/polibits/article/view/45-3/1743","source":{"id":"https://openalex.org/S4210186437","display_name":"Polibits","issn_l":"1870-9044","issn":["1870-9044","2395-8618"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Polibits","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1923382164.pdf","grobid_xml":"https://content.openalex.org/works/W1923382164.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W618790303","https://openalex.org/W1513146288","https://openalex.org/W1522405883","https://openalex.org/W1530303756","https://openalex.org/W1542597404","https://openalex.org/W1567087985","https://openalex.org/W1569123402","https://openalex.org/W1956641659","https://openalex.org/W2005876975","https://openalex.org/W2011798344","https://openalex.org/W2012833704","https://openalex.org/W2067432306","https://openalex.org/W2085922539","https://openalex.org/W2087064593","https://openalex.org/W2145349611","https://openalex.org/W2153305383","https://openalex.org/W2166681397","https://openalex.org/W4302352838","https://openalex.org/W6651750703","https://openalex.org/W6653299410","https://openalex.org/W6681490311","https://openalex.org/W7019408341"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Near-duplicate":[0],"detection":[1],"is":[2],"important":[3],"when":[4],"dealing":[5],"with":[6,31,43],"large,":[7],"noisy":[8],"databases":[9],"in":[10],"data":[11,47],"mining":[12],"tasks.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17],"present":[18],"the":[19,23,27,39,50],"results":[20],"of":[21,52],"applying":[22],"Rank":[24],"distance":[25],"and":[26],"Smith-Waterman":[28],"distance,":[29,41],"along":[30],"more":[32],"popular":[33],"string":[34],"similarity":[35],"measures":[36],"such":[37],"as":[38],"Levenshtein":[40],"together":[42],"a":[44],"disjoint":[45],"set":[46],"structure,":[48],"for":[49],"problem":[51],"near-duplicate":[53],"detection.":[54]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
