{"id":"https://openalex.org/W2727277874","doi":"https://doi.org/10.4149/cai_2017_3_683","title":"Efficient String Edit Similarity Join Algorithm","display_name":"Efficient String Edit Similarity Join Algorithm","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2727277874","doi":"https://doi.org/10.4149/cai_2017_3_683","mag":"2727277874"},"language":"en","primary_location":{"id":"doi:10.4149/cai_2017_3_683","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2017_3_683","pdf_url":null,"source":{"id":"https://openalex.org/S6236348","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4360969452","host_organization_name":"Institute of Informatics","host_organization_lineage":["https://openalex.org/P4360969452","https://openalex.org/P4310314449"],"host_organization_lineage_names":["Institute of Informatics","Slovak Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4149/cai_2017_3_683","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048610953","display_name":"Karam Gouda","orcid":null},"institutions":[{"id":"https://openalex.org/I207547235","display_name":"Benha University","ror":"https://ror.org/03tn5ee41","country_code":"EG","type":"education","lineage":["https://openalex.org/I207547235"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Karam Gouda","raw_affiliation_strings":["Faculty of Computers and Informatics, Benha University, Benha"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Informatics, Benha University, Benha","institution_ids":["https://openalex.org/I207547235"]}]},{"author_position":"last","author":{"id":null,"display_name":"Metwally Rashad","orcid":null},"institutions":[{"id":"https://openalex.org/I140275651","display_name":"University of Pannonia","ror":"https://ror.org/03y5egs41","country_code":"HU","type":"education","lineage":["https://openalex.org/I140275651"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Metwally Rashad","raw_affiliation_strings":["Faculty of Information Technology, University of Pannonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Pannonia","institution_ids":["https://openalex.org/I140275651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6317,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77394266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"36","issue":"3","first_page":"683","last_page":"704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9925000071525574,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9918000102043152,"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/trie","display_name":"Trie","score":0.9302513599395752},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.8103358745574951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7393790483474731},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.6689062118530273},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6669214367866516},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5569663047790527},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5424062609672546},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5349043607711792},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5008091926574707},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48577025532722473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47687655687332153},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.427898108959198},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.24587160348892212},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20219895243644714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16712254285812378},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08407938480377197},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06984022259712219}],"concepts":[{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.9302513599395752},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.8103358745574951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393790483474731},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.6689062118530273},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6669214367866516},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5569663047790527},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5424062609672546},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5349043607711792},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5008091926574707},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48577025532722473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47687655687332153},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.427898108959198},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.24587160348892212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20219895243644714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16712254285812378},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08407938480377197},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06984022259712219},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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:10.4149/cai_2017_3_683","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2017_3_683","pdf_url":null,"source":{"id":"https://openalex.org/S6236348","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4360969452","host_organization_name":"Institute of Informatics","host_organization_lineage":["https://openalex.org/P4360969452","https://openalex.org/P4310314449"],"host_organization_lineage_names":["Institute of Informatics","Slovak Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4149/cai_2017_3_683","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2017_3_683","pdf_url":null,"source":{"id":"https://openalex.org/S6236348","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4360969452","host_organization_name":"Institute of Informatics","host_organization_lineage":["https://openalex.org/P4360969452","https://openalex.org/P4310314449"],"host_organization_lineage_names":["Institute of Informatics","Slovak Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2727277874","https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2405436873","https://openalex.org/W2131677984","https://openalex.org/W52396946","https://openalex.org/W1973578339","https://openalex.org/W1824878879","https://openalex.org/W1998140328","https://openalex.org/W1979059701"],"abstract_inverted_index":{"String":[0],"similarity":[1,21,30,47],"join":[2,22,31,48,105,114,213],"is":[3,44,55,151,165,182,197],"a":[4,81,102,124,158,176,216],"basic":[5],"and":[6,59,65,208],"essential":[7],"operation":[8],"in":[9,80,143,153],"many":[10],"applications.":[11],"In":[12,97],"this":[13,98],"paper,":[14,99],"we":[15,100],"investigate":[16],"the":[17,89,131,139,144,162,169,210],"problem":[18,54],"of":[19,40,68,91,133,149,161,179],"string":[20,121,173,180],"with":[23],"edit":[24,29,87,189],"distance":[25,190],"constraints.":[26],"A":[27],"trie-based":[28,42,104,113,212],"framework":[32],"has":[33],"been":[34],"proposed":[35],"recently.":[36],"The":[37,52,147],"main":[38,53],"advantage":[39],"existing":[41],"algorithms":[43],"support":[45],"for":[46,171,200],"on":[49,187],"short":[50,202],"strings.":[51,61],"when":[56],"joining":[57],"long":[58,206],"distant":[60],"These":[62],"methods":[63],"generate":[64],"maintain":[66],"lots":[67],"similar":[69,120,172],"prefixes":[70],"called":[71,107],"active":[72,92,135],"nodes":[73,93,136],"which":[74,109,129],"need":[75],"to":[76,167,184],"be":[77],"further":[78],"removed":[79],"subsequent":[82],"pruning":[83,140],"phase.":[84],"With":[85],"large":[86,188],"distance,":[88],"number":[90,132],"becomes":[94],"quite":[95],"large.":[96],"propose":[101],"new":[103],"algorithm":[106],"PreJoin,":[108],"improves":[110],"upon":[111],"current":[112],"methods.":[115],"It":[116],"efficiently":[117],"finds":[118],"all":[119],"pairs":[122],"using":[123],"novel":[125],"active-node":[126],"generation":[127,145],"method,":[128],"minimizes":[130],"generated":[134],"by":[137,215],"applying":[138],"heuristics":[141],"early":[142],"process.":[146],"performance":[148,186],"PreJoin":[150],"scaled":[152],"two":[154],"different":[155],"ways:":[156],"First,":[157],"dynamic":[159],"reordering":[160],"trie":[163],"index":[164],"used":[166,183],"accelerate":[168],"search":[170],"pairs.":[174],"Second,":[175],"partitioning":[177],"method":[178],"space":[181],"improve":[185],"thresholds.":[191],"Experiments":[192],"show":[193],"that":[194],"our":[195],"approach":[196],"highly":[198],"efficient":[199],"processing":[201],"as":[203,205],"well":[204],"strings,":[207],"outperforms":[209],"state-of-the-art":[211],"approaches":[214],"factor":[217],"five.":[218]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}
