{"id":"https://openalex.org/W2207847180","doi":"https://doi.org/10.14778/2824032.2824049","title":"Fuzzy joins in MapReduce","display_name":"Fuzzy joins in MapReduce","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2207847180","doi":"https://doi.org/10.14778/2824032.2824049","mag":"2207847180"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824049","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824049","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5037891879","display_name":"Ben Kimmett","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ben Kimmett","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101961455","display_name":"Venkatesh Srinivasan","orcid":"https://orcid.org/0000-0003-3819-3998"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Venkatesh Srinivasan","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011013528","display_name":"Alex Thomo","orcid":"https://orcid.org/0000-0002-3020-2258"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alex Thomo","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I212119943"],"apc_list":null,"apc_paid":null,"fwci":2.4379,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91504512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":"12","first_page":"1514","last_page":"1517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9986000061035156,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9986000061035156,"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":0.9940999746322632,"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/T11106","display_name":"Data Management and Algorithms","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/joins","display_name":"Joins","score":0.9206621050834656},{"id":"https://openalex.org/keywords/skyline","display_name":"Skyline","score":0.8143680095672607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7944293022155762},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.604209840297699},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.6009193062782288},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.481557160615921},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4797300398349762},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4388422667980194},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4001643657684326},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3860586881637573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24717342853546143},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14474689960479736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07979169487953186},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.07327309250831604}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9206621050834656},{"id":"https://openalex.org/C2780757406","wikidata":"https://www.wikidata.org/wiki/Q465837","display_name":"Skyline","level":2,"score":0.8143680095672607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944293022155762},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.604209840297699},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.6009193062782288},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.481557160615921},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4797300398349762},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4388422667980194},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4001643657684326},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3860586881637573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24717342853546143},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14474689960479736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07979169487953186},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.07327309250831604},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2824032.2824049","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824049","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2169387919"],"related_works":["https://openalex.org/W1994126304","https://openalex.org/W2087306197","https://openalex.org/W1973297295","https://openalex.org/W2316530548","https://openalex.org/W2505069962","https://openalex.org/W3096764880","https://openalex.org/W2039842051","https://openalex.org/W2317048282","https://openalex.org/W102592377","https://openalex.org/W1580710993"],"abstract_inverted_index":{"We":[0,69,88],"report":[1],"experimental":[2,38,91],"results":[3,92],"for":[4],"the":[5,62,97],"MapReduce":[6],"algorithms":[7,30,81],"proposed":[8,63],"by":[9],"Afrati,":[10],"Das":[11],"Sarma,":[12],"Menestrina,":[13],"Parameswaran":[14],"and":[15,52,55,93],"Ullman":[16],"in":[17],"ICDE'12":[18],"to":[19,86],"compute":[20],"fuzzy":[21],"joins":[22],"of":[23,61,78,100],"binary":[24],"strings":[25],"using":[26],"Hamming":[27],"Distance.":[28],"Their":[29],"come":[31],"with":[32],"complete":[33],"theoretical":[34],"analysis,":[35],"however,":[36],"no":[37],"evaluation":[39],"is":[40,46,58],"provided.":[41],"They":[42],"argue":[43],"that":[44,56,95],"there":[45,57],"a":[47,59,75],"tradeoff":[48],"between":[49],"communication":[50],"cost":[51],"processing":[53],"cost,":[54],"skyline":[60],"algorithms;":[64],"i.e.":[65],"none":[66],"dominates":[67],"another.":[68],"observe":[70],"via":[71],"experiments":[72],"that,":[73],"from":[74],"practical":[76],"point":[77],"view,":[79],"some":[80],"are":[82],"almost":[83],"always":[84],"preferable":[85],"others.":[87],"provide":[89],"detailed":[90],"insights":[94],"show":[96],"different":[98],"facets":[99],"each":[101],"algorithm.":[102]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
