{"id":"https://openalex.org/W2101341488","doi":"https://doi.org/10.1109/msr.2009.5069477","title":"MapReduce as a general framework to support research in Mining Software Repositories (MSR)","display_name":"MapReduce as a general framework to support research in Mining Software Repositories (MSR)","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2101341488","doi":"https://doi.org/10.1109/msr.2009.5069477","mag":"2101341488"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2009.5069477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","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/A5056378414","display_name":"Weiyi Shang","orcid":"https://orcid.org/0000-0001-6222-7444"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiyi Shang","raw_affiliation_strings":["Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085576468","display_name":"Zhen Ming Jiang","orcid":"https://orcid.org/0000-0002-3063-3197"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhen Ming Jiang","raw_affiliation_strings":["Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058164381","display_name":"Bram Adams","orcid":"https://orcid.org/0000-0001-7213-4006"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bram Adams","raw_affiliation_strings":["Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091586373","display_name":"Ahmed E. Hassan","orcid":"https://orcid.org/0000-0001-7749-5513"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed E. Hassan","raw_affiliation_strings":["Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Analysis and Intelligence Laboratory (SAIL, Queen''s University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Software Analysis and Intelligence Lab (SAIL) Queen's University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.9758,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.98616744,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","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/T10260","display_name":"Software Engineering Research","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/T12127","display_name":"Software System Performance and Reliability","score":0.9894000291824341,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8403704166412354},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7670867443084717},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6412011981010437},{"id":"https://openalex.org/keywords/eclipse","display_name":"Eclipse","score":0.6248950362205505},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6008451581001282},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5383106470108032},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48821118474006653},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4814128875732422},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4663856029510498},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.42862600088119507},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41501277685165405},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41366150975227356},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3656389117240906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403704166412354},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7670867443084717},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6412011981010437},{"id":"https://openalex.org/C2778505590","wikidata":"https://www.wikidata.org/wiki/Q141022","display_name":"Eclipse","level":2,"score":0.6248950362205505},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6008451581001282},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5383106470108032},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48821118474006653},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4814128875732422},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4663856029510498},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.42862600088119507},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41501277685165405},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41366150975227356},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3656389117240906},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msr.2009.5069477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1533432827","https://openalex.org/W1536082920","https://openalex.org/W1677598599","https://openalex.org/W1853827169","https://openalex.org/W2049828091","https://openalex.org/W2104644701","https://openalex.org/W2110307645","https://openalex.org/W2115398138","https://openalex.org/W2116255095","https://openalex.org/W2119565742","https://openalex.org/W2120160565","https://openalex.org/W2128780139","https://openalex.org/W2131629857","https://openalex.org/W2136112704","https://openalex.org/W2138756793","https://openalex.org/W2162520939","https://openalex.org/W2172244770","https://openalex.org/W2173213060","https://openalex.org/W2320958330","https://openalex.org/W4239670432","https://openalex.org/W6662884684","https://openalex.org/W6677135450"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2611067230","https://openalex.org/W2480201319","https://openalex.org/W2387706296","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W2770234245","https://openalex.org/W2383892934"],"abstract_inverted_index":{"Researchers":[0],"continue":[1],"to":[2,39,52,74,90,122,142],"demonstrate":[3,117],"the":[4,20,66,105,110,119,128,136,145,154,158,163,167],"benefits":[5,129,159],"of":[6,68,98,109,135,144,162],"Mining":[7],"Software":[8],"Repositories":[9],"(MSR)":[10],"for":[11],"supporting":[12],"software":[13],"development":[14],"and":[15,25,35,42,54,58,113,126,156,160],"research":[16,76],"activities.":[17],"However,":[18],"as":[19,132],"mining":[21],"process":[22],"is":[23,124,139],"time":[24,134],"resource":[26],"intensive,":[27],"they":[28],"often":[29],"create":[30],"their":[31,45],"own":[32],"distributed":[33,71],"platforms":[34,48],"use":[36,67],"various":[37],"optimizations":[38],"speed":[40],"up":[41,44],"scale":[43],"analysis.":[46],"These":[47],"are":[49,130],"project-specific,":[50],"hard":[51],"reuse,":[53],"offer":[55],"minimal":[56,125],"debugging":[57],"deployment":[59],"support.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,82,116],"propose":[65],"MapReduce,":[69],"a":[70,80,101],"computing":[72],"platform,":[73],"support":[75],"in":[77,166],"MSR.":[78],"As":[79],"proof-of-concept,":[81],"migrate":[83],"J-REX,":[84],"an":[85,94],"optimized":[86],"evolutionary":[87],"code":[88],"extractor,":[89],"run":[91],"on":[92,104],"Hadoop,":[93],"open":[95],"source":[96,106],"implementation":[97],"MapReduce.":[99],"Through":[100],"case":[102],"study":[103],"control":[107],"repositories":[108],"Eclipse,":[111],"BIRT":[112],"Datatools":[114],"projects,":[115],"that":[118,127],"migration":[120],"effort":[121],"MapReduce":[123,164],"significant,":[131],"running":[133],"migrated":[137],"J-REX":[138],"only":[140],"30%":[141],"50%":[143],"original":[146],"J-REX's.":[147],"This":[148],"paper":[149],"documents":[150],"our":[151],"experience":[152],"with":[153],"migration,":[155],"highlights":[157],"challenges":[161],"framework":[165],"MSR":[168],"community.":[169]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
