{"id":"https://openalex.org/W2023907149","doi":"https://doi.org/10.1109/msr.2010.5463286","title":"When process data quality affects the number of bugs: Correlations in software engineering datasets","display_name":"When process data quality affects the number of bugs: Correlations in software engineering datasets","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2023907149","doi":"https://doi.org/10.1109/msr.2010.5463286","mag":"2023907149"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2010.5463286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2010.5463286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090966134","display_name":"Adrian Bachmann","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Adrian Bachmann","raw_affiliation_strings":["Department of Informatics, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073592405","display_name":"Abraham Bernstein","orcid":"https://orcid.org/0000-0002-0128-4602"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Abraham Bernstein","raw_affiliation_strings":["Department of Informatics, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090966134"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":4.8559,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95314942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.656531572341919},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.6102465987205505},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5817066431045532},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.5472851991653442},{"id":"https://openalex.org/keywords/software-quality-analyst","display_name":"Software quality analyst","score":0.5389770269393921},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49959516525268555},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.4652387201786041},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4532545208930969},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4504556953907013},{"id":"https://openalex.org/keywords/software-quality-control","display_name":"Software quality control","score":0.4345259666442871},{"id":"https://openalex.org/keywords/team-software-process","display_name":"Team software process","score":0.4128447473049164},{"id":"https://openalex.org/keywords/software-development-process","display_name":"Software development process","score":0.39956820011138916},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.37448304891586304},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.35695916414260864},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3277798891067505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27125585079193115},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20917800068855286},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.08028975129127502},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07385623455047607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656531572341919},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.6102465987205505},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5817066431045532},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.5472851991653442},{"id":"https://openalex.org/C188329197","wikidata":"https://www.wikidata.org/wiki/Q6554613","display_name":"Software quality analyst","level":5,"score":0.5389770269393921},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49959516525268555},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.4652387201786041},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4532545208930969},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4504556953907013},{"id":"https://openalex.org/C176035894","wikidata":"https://www.wikidata.org/wiki/Q7554350","display_name":"Software quality control","level":5,"score":0.4345259666442871},{"id":"https://openalex.org/C51845450","wikidata":"https://www.wikidata.org/wiki/Q1421651","display_name":"Team software process","level":5,"score":0.4128447473049164},{"id":"https://openalex.org/C180152950","wikidata":"https://www.wikidata.org/wiki/Q2904257","display_name":"Software development process","level":4,"score":0.39956820011138916},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.37448304891586304},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.35695916414260864},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3277798891067505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27125585079193115},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20917800068855286},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.08028975129127502},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07385623455047607},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/msr.2010.5463286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2010.5463286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.zora.uzh.ch:44839","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Bernstein, Abraham; Bachmann, Adrian  (2010). When process data quality affects the number of bugs: correlations in software engineering datasets.  In: MSR '10: 7th IEEE Working Conference on Mining Software Repositories, Cape Town, South Africa, 2010, 62-71.","raw_type":"Conference or Workshop Item"},{"id":"doi:10.5167/uzh-44839","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-44839","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:www.zora.uzh.ch:44839","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Bernstein, Abraham; Bachmann, Adrian  (2010). When process data quality affects the number of bugs: correlations in software engineering datasets.  In: MSR '10: 7th IEEE Working Conference on Mining Software Repositories, Cape Town, South Africa, 2010, 62-71.","raw_type":"Conference or Workshop Item"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1961908490","https://openalex.org/W1985514943","https://openalex.org/W2000241667","https://openalex.org/W2025674334","https://openalex.org/W2036296745","https://openalex.org/W2055186786","https://openalex.org/W2059621895","https://openalex.org/W2095032754","https://openalex.org/W2096205144","https://openalex.org/W2102013000","https://openalex.org/W2107031757","https://openalex.org/W2110385988","https://openalex.org/W2112779014","https://openalex.org/W2114363693","https://openalex.org/W2122696684","https://openalex.org/W2124797841","https://openalex.org/W2127577307","https://openalex.org/W2134982005","https://openalex.org/W2142481192","https://openalex.org/W2143059009","https://openalex.org/W2149783794","https://openalex.org/W2151187574","https://openalex.org/W2157353183","https://openalex.org/W2158133897","https://openalex.org/W2159610968","https://openalex.org/W2160517961","https://openalex.org/W2167830984","https://openalex.org/W2171733741","https://openalex.org/W4235354960","https://openalex.org/W4239181501","https://openalex.org/W4240402692","https://openalex.org/W4241947741","https://openalex.org/W6640891668","https://openalex.org/W6683485314"],"related_works":["https://openalex.org/W4245217388","https://openalex.org/W2342006181","https://openalex.org/W2642920007","https://openalex.org/W2142304735","https://openalex.org/W2323318447","https://openalex.org/W4206779626","https://openalex.org/W2052786937","https://openalex.org/W2112269074","https://openalex.org/W2186591298","https://openalex.org/W2314568099"],"abstract_inverted_index":{"Software":[0],"engineering":[1,67],"process":[2,87,99,104,110,137,185,204],"information":[3],"extracted":[4],"from":[5],"version":[6],"control":[7],"systems":[8],"and":[9,90,100,134,140,205],"bug":[10,97,147,164],"tracking":[11],"databases":[12],"are":[13,28],"widely":[14],"used":[15],"in":[16,35,47,58,157],"empirical":[17,59],"software":[18,60,66,203],"engineering.":[19,61],"In":[20,40,78],"prior":[21],"work,":[22],"we":[23,42,122],"showed":[24,43],"that":[25,44,136,170],"these":[26,63],"data":[27,88,111,138,186,208],"plagued":[29],"by":[30,108,176,184],"quality":[31,89,105,139,173,187,200],"deficiencies,":[32],"which":[33],"vary":[34],"its":[36,206],"characteristics":[37,91,141],"across":[38],"projects.":[39],"addition,":[41],"those":[45],"deficiencies":[46],"the":[48,54,69,86,96,103,109,116,146,150,163,171,192,199],"form":[49],"of":[50,56,153,178,201],"bias":[51],"do":[52],"impact":[53,70,144],"results":[55],"studies":[57],"While":[62],"findings":[64,190],"affect":[65],"researchers":[68],"on":[71,95,115,145],"practitioners":[72,196],"has":[73,112],"not":[74],"yet":[75],"been":[76],"substantiated.":[77],"this":[79],"paper":[80],"we,":[81],"therefore,":[82],"explore":[83],"(i)":[84],"if":[85,102],"have":[92,142,191],"an":[93,113,143],"influence":[94,114],"fixing":[98,148],"(ii)":[101],"as":[106,127,129],"measured":[107,175],"product":[117,172],"(i.e.,":[118],"software)":[119],"quality.":[120,166,209],"Specifically,":[121],"analyze":[123],"six":[124],"Open":[125],"Source":[126,132],"well":[128],"two":[130],"Closed":[131],"projects":[133],"show":[135,169],"process:":[149],"high":[151],"rate":[152],"empty":[154],"commit":[155],"messages":[156],"Eclipse,":[158],"for":[159],"example,":[160],"correlates":[161],"with":[162],"report":[165],"We":[167],"also":[168],"-":[174,181],"number":[177],"bugs":[179],"reported":[180],"is":[182],"affected":[183],"measures.":[188],"These":[189],"potential":[193],"to":[194,197],"prompt":[195],"increase":[198],"their":[202],"associated":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}