{"id":"https://openalex.org/W2565034015","doi":"https://doi.org/10.1109/iisa.2016.7785408","title":"Fuzzy joins in MapReduce: Edit and Jaccard distance","display_name":"Fuzzy joins in MapReduce: Edit and Jaccard distance","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2565034015","doi":"https://doi.org/10.1109/iisa.2016.7785408","mag":"2565034015"},"language":"en","primary_location":{"id":"doi:10.1109/iisa.2016.7785408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisa.2016.7785408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 7th International Conference on Information, Intelligence, Systems & Applications (IISA)","raw_type":"proceedings-article"},"type":"conference-paper","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, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","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, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","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, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, BC, 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":0.2621,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53899637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9976999759674072,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9937999844551086,"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/jaccard-index","display_name":"Jaccard index","score":0.9714714288711548},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8219065070152283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8082261085510254},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.7763277888298035},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7414201498031616},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5989657044410706},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.4387713372707367},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4177587628364563},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.40642109513282776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36798661947250366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3561299443244934},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3342939615249634},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09305542707443237},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07394871115684509}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9714714288711548},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8219065070152283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082261085510254},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7763277888298035},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7414201498031616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5989657044410706},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.4387713372707367},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4177587628364563},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.40642109513282776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36798661947250366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3561299443244934},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3342939615249634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09305542707443237},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07394871115684509},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iisa.2016.7785408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisa.2016.7785408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 7th International Conference on Information, Intelligence, Systems & Applications (IISA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W71244820","https://openalex.org/W171520349","https://openalex.org/W822439496","https://openalex.org/W1511951313","https://openalex.org/W1512553031","https://openalex.org/W1545348482","https://openalex.org/W1549099081","https://openalex.org/W1812036194","https://openalex.org/W1913567977","https://openalex.org/W1930175493","https://openalex.org/W1974625623","https://openalex.org/W1981787615","https://openalex.org/W2017533400","https://openalex.org/W2025605741","https://openalex.org/W2031600655","https://openalex.org/W2053024197","https://openalex.org/W2065259291","https://openalex.org/W2079971532","https://openalex.org/W2097184821","https://openalex.org/W2121269638","https://openalex.org/W2145812340","https://openalex.org/W2151930506","https://openalex.org/W2161118616","https://openalex.org/W2169387919","https://openalex.org/W2207847180","https://openalex.org/W2216499221","https://openalex.org/W2219888463","https://openalex.org/W2260484439","https://openalex.org/W2962712636","https://openalex.org/W6623203846","https://openalex.org/W6640144873","https://openalex.org/W6640183032","https://openalex.org/W6917172014"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W1994775821","https://openalex.org/W2775696757","https://openalex.org/W2172084996","https://openalex.org/W2012019886"],"abstract_inverted_index":{"In":[0,15],"ICDE'12,":[1],"Afrati,":[2],"Das":[3],"Sarma,":[4],"Menestrina,":[5],"Parameswaran":[6],"and":[7,20,31,58],"Ullman":[8],"proposed":[9,26],"similarity":[10,47],"join":[11],"algorithms":[12,27,43,61],"for":[13],"MapReduce.":[14,71],"this":[16],"paper,":[17],"we":[18],"evaluate":[19,59],"extend":[21],"their":[22,25,42],"research,":[23],"testing":[24],"using":[28],"edit":[29],"distance":[30],"Jaccard":[32],"similarity.":[33],"We":[34,49],"provide":[35],"details":[36],"of":[37],"adaptations":[38],"needed":[39],"to":[40],"implement":[41],"based":[44],"on":[45,55],"these":[46],"measures.":[48],"conduct":[50],"an":[51],"extensive":[52],"experimental":[53],"study":[54],"large":[56],"datasets":[57],"the":[60,67],"across":[62],"several":[63],"dimensions":[64],"that":[65],"define":[66],"performance":[68],"profile":[69],"in":[70]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}