{"id":"https://openalex.org/W2043099794","doi":"https://doi.org/10.1145/1807167.1807273","title":"A comparison of join algorithms for log processing in MaPreduce","display_name":"A comparison of join algorithms for log processing in MaPreduce","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2043099794","doi":"https://doi.org/10.1145/1807167.1807273","mag":"2043099794"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","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/A5001035930","display_name":"Spyros Blanas","orcid":"https://orcid.org/0009-0004-2703-7177"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Spyros Blanas","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065055611","display_name":"Vuk Ercegovac","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vuk Ercegovac","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009094344","display_name":"Jun Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Rao","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047853212","display_name":"Eugene J. Shekita","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene J. Shekita","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090562336","display_name":"Yuanyuan Tian","orcid":"https://orcid.org/0000-0002-6835-8434"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanyuan Tian","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001035930"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":92.1215,"has_fulltext":false,"cited_by_count":411,"citation_normalized_percentile":{"value":0.99937708,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"975","last_page":"986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.994700014591217,"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":0.9536285400390625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8966450691223145},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.8485369682312012},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.48822644352912903},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4458942711353302},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38232430815696716},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3638031482696533},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35334497690200806},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3489171862602234},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14039689302444458}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9536285400390625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8966450691223145},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8485369682312012},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.48822644352912903},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4458942711353302},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38232430815696716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3638031482696533},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35334497690200806},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3489171862602234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14039689302444458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1807167.1807273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1582870960","https://openalex.org/W1997020216","https://openalex.org/W2015372451","https://openalex.org/W2023195086","https://openalex.org/W2078528123","https://openalex.org/W2098935637","https://openalex.org/W2114303224","https://openalex.org/W2119400430","https://openalex.org/W2119565742","https://openalex.org/W2154894831","https://openalex.org/W2158237121","https://openalex.org/W2173213060","https://openalex.org/W4238584892","https://openalex.org/W4238594802"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"The":[0],"MapReduce":[1,21,75,81,133],"framework":[2,76],"is":[3,22,33,77],"increasingly":[4],"being":[5],"used":[6],"to":[7,49,89,131,140],"analyze":[8],"large":[9],"volumes":[10],"of":[11,16,42,100,103,115],"data.":[12],"One":[13],"important":[14],"type":[15],"data":[17,54],"analysis":[18],"done":[19],"with":[20,52],"log":[23,32,46],"processing,":[24],"in":[25,69,107],"which":[26],"a":[27,101,111,120,142],"click-stream":[28],"or":[29,36],"an":[30],"event":[31],"filtered,":[34],"aggregated,":[35],"mined":[37],"for":[38,79],"patterns.":[39],"As":[40],"part":[41],"this":[43,93,147],"analysis,":[44],"the":[45,74,132],"often":[47,83],"needs":[48],"be":[50],"joined":[51],"reference":[53],"such":[55],"as":[56],"information":[57],"about":[58],"users.":[59],"Although":[60],"there":[61],"have":[62],"been":[63],"many":[64],"studies":[65],"examining":[66],"join":[67,105,117,144],"algorithms":[68,88],"parallel":[70],"and":[71,109,135],"distributed":[72],"DBMSs,":[73],"cumbersome":[78],"joins.":[80,91],"programmers":[82],"use":[84,141],"simple":[85],"but":[86],"inefficient":[87],"perform":[90],"In":[92],"paper,":[94],"we":[95],"describe":[96],"crucial":[97],"implementation":[98],"details":[99],"number":[102],"well-known":[104],"strategies":[106],"MapReduce,":[108],"present":[110],"comprehensive":[112],"experimental":[113],"comparison":[114],"these":[116],"techniques":[118],"on":[119,138,146],"100-node":[121],"Hadoop":[122],"cluster.":[123],"Our":[124],"results":[125],"provide":[126],"insights":[127],"that":[128],"are":[129],"unique":[130],"platform":[134],"offer":[136],"guidance":[137],"when":[139],"particular":[143],"algorithm":[145],"platform.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":43},{"year":2015,"cited_by_count":45},{"year":2014,"cited_by_count":69},{"year":2013,"cited_by_count":61},{"year":2012,"cited_by_count":45}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
