{"id":"https://openalex.org/W2117508687","doi":"https://doi.org/10.1145/1858996.1859050","title":"An experience report on scaling tools for mining software repositories using MapReduce","display_name":"An experience report on scaling tools for mining software repositories using MapReduce","publication_year":2010,"publication_date":"2010-09-20","ids":{"openalex":"https://openalex.org/W2117508687","doi":"https://doi.org/10.1145/1858996.1859050","mag":"2117508687"},"language":"en","primary_location":{"id":"doi:10.1145/1858996.1859050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1858996.1859050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM international conference on Automated software engineering","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":true,"raw_author_name":"Weiyi Shang","raw_affiliation_strings":["Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, ON, 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":["Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, ON, 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":["Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056378414"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":9.2928,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97749724,"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":"275","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958999752998352,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.7931913733482361},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6731637716293335},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.6279327273368835},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5911546945571899},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5823289155960083},{"id":"https://openalex.org/keywords/search-based-software-engineering","display_name":"Search-based software engineering","score":0.5186104774475098},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4440571069717407},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42578452825546265},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.42389070987701416},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.3633785843849182},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.35427945852279663},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30951082706451416},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12984707951545715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08094775676727295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931913733482361},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6731637716293335},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.6279327273368835},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5911546945571899},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5823289155960083},{"id":"https://openalex.org/C139143892","wikidata":"https://www.wikidata.org/wiki/Q7441615","display_name":"Search-based software engineering","level":5,"score":0.5186104774475098},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4440571069717407},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42578452825546265},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.42389070987701416},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3633785843849182},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.35427945852279663},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30951082706451416},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12984707951545715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08094775676727295},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1858996.1859050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1858996.1859050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM international conference on Automated software engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.482.9096","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.482.9096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sail.cs.queensu.ca/publications/pubs/ase2010-shang.pdf/at_download/file/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W157156687","https://openalex.org/W1484473245","https://openalex.org/W1510543252","https://openalex.org/W1598064945","https://openalex.org/W1730627516","https://openalex.org/W1850047186","https://openalex.org/W2008164297","https://openalex.org/W2009327396","https://openalex.org/W2044490410","https://openalex.org/W2049828091","https://openalex.org/W2051831304","https://openalex.org/W2092382400","https://openalex.org/W2098935637","https://openalex.org/W2099677903","https://openalex.org/W2101341488","https://openalex.org/W2101414596","https://openalex.org/W2101832700","https://openalex.org/W2106122655","https://openalex.org/W2110307645","https://openalex.org/W2116255095","https://openalex.org/W2121972257","https://openalex.org/W2122435938","https://openalex.org/W2138756793","https://openalex.org/W2141482658","https://openalex.org/W2146136779","https://openalex.org/W2152759400","https://openalex.org/W2169917206","https://openalex.org/W2170114245","https://openalex.org/W2171683519","https://openalex.org/W2172244770","https://openalex.org/W2173213060","https://openalex.org/W4231671330","https://openalex.org/W4232276817","https://openalex.org/W4243800908","https://openalex.org/W6606430823","https://openalex.org/W6635687051"],"related_works":["https://openalex.org/W2783065147","https://openalex.org/W4312723892","https://openalex.org/W3173949332","https://openalex.org/W4214835859","https://openalex.org/W4312927049","https://openalex.org/W2380017313","https://openalex.org/W2520111506","https://openalex.org/W2359702179","https://openalex.org/W2366623749","https://openalex.org/W39186842"],"abstract_inverted_index":{"The":[0,56],"need":[1,57,159],"for":[2,58,154],"automated":[3,75,94],"software":[4,84,95,169],"engineering":[5,25,96,170],"tools":[6,129],"and":[7,15,20,50,77],"techniques":[8,22,31,40,98],"continues":[9],"to":[10,54,118,126,160,163],"grow":[11],"as":[12],"the":[13,65,74,91,105,115,120,123,150,156,166],"size":[14],"complexity":[16],"of":[17,79,93,122,149,168],"studied":[18],"systems":[19],"analysis":[21,30,60,78,97,102],"increase.":[23],"Software":[24,67],"researchers":[26,140],"often":[27,52],"scale":[28,127],"their":[29],"using":[32,155],"specialized":[33],"one-off":[34],"solutions,":[35],"expensive":[36],"infrastructures,":[37],"or":[38],"heuristic":[39],"(e.g.,":[41],"search-based":[42],"approaches).":[43],"However,":[44],"such":[45,137],"efforts":[46],"are":[47,51],"not":[48],"reusable":[49],"costly":[53],"maintain.":[55],"scalable":[59,101],"is":[61],"very":[62],"prominent":[63],"in":[64,73,83],"Mining":[66],"Repositories":[68],"(MSR)":[69],"field,":[70],"which":[71],"specializes":[72],"recovery":[76],"large":[80],"data":[81],"stored":[82],"repositories.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"explore":[90],"scaling":[92],"by":[99],"reusing":[100],"platforms":[103],"from":[104,114,143],"web":[106,151],"field.":[107],"We":[108,133,145],"use":[109],"three":[110],"representative":[111],"case":[112],"studies":[113],"MSR":[116,128],"field":[117],"analyze":[119],"potential":[121],"MapReduce":[124,157],"platform":[125,158],"with":[130],"minimal":[131],"effort.":[132],"document":[134],"our":[135],"experience":[136],"that":[138,147],"other":[139],"could":[141],"benefit":[142],"them.":[144],"find":[146],"many":[148],"field's":[152],"guidelines":[153],"be":[161],"modified":[162],"better":[164],"fit":[165],"characteristics":[167],"problems.":[171]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
