{"id":"https://openalex.org/W2510885373","doi":"https://doi.org/10.1109/tse.2016.2599161","title":"The Use of Summation to Aggregate Software Metrics Hinders the Performance of Defect Prediction Models","display_name":"The Use of Summation to Aggregate Software Metrics Hinders the Performance of Defect Prediction Models","publication_year":2016,"publication_date":"2016-08-10","ids":{"openalex":"https://openalex.org/W2510885373","doi":"https://doi.org/10.1109/tse.2016.2599161","mag":"2510885373"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2016.2599161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2016.2599161","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-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/A5019624408","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0001-9805-395X"},"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":"Feng Zhang","raw_affiliation_strings":["School of Computing, Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computing, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","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":["School of Computing, Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computing, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043053174","display_name":"Shane McIntosh","orcid":"https://orcid.org/0000-0002-0193-3975"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shane McIntosh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101468895","display_name":"Ying Zou","orcid":"https://orcid.org/0000-0002-5335-0261"},"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":"Ying Zou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019624408"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":21.2312,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.99314464,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"43","issue":"5","first_page":"476","last_page":"491"},"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":0.9957000017166138,"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":0.9879000186920166,"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/cyclomatic-complexity","display_name":"Cyclomatic complexity","score":0.8262978792190552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8215717673301697},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6508693695068359},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.6378764510154724},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6229076981544495},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.607405960559845},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5764041543006897},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.500800609588623},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.49101948738098145},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.4876631498336792},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.46890321373939514},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.44174709916114807},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.4201869070529938},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3651088774204254},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33197447657585144},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.3050397038459778},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.2501125931739807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2196495532989502},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17138639092445374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12094229459762573}],"concepts":[{"id":"https://openalex.org/C187303228","wikidata":"https://www.wikidata.org/wiki/Q867330","display_name":"Cyclomatic complexity","level":3,"score":0.8262978792190552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215717673301697},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6508693695068359},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.6378764510154724},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6229076981544495},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.607405960559845},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5764041543006897},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.500800609588623},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49101948738098145},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.4876631498336792},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.46890321373939514},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.44174709916114807},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.4201869070529938},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3651088774204254},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33197447657585144},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.3050397038459778},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2501125931739807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2196495532989502},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17138639092445374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12094229459762573},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2016.2599161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2016.2599161","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W168970045","https://openalex.org/W1600199800","https://openalex.org/W1964731418","https://openalex.org/W1964962870","https://openalex.org/W1969319425","https://openalex.org/W1974601952","https://openalex.org/W1975503357","https://openalex.org/W1978813754","https://openalex.org/W1981796233","https://openalex.org/W1982004548","https://openalex.org/W1994248747","https://openalex.org/W1995875735","https://openalex.org/W1995945562","https://openalex.org/W2008596407","https://openalex.org/W2014737582","https://openalex.org/W2025043404","https://openalex.org/W2029123435","https://openalex.org/W2030857403","https://openalex.org/W2032375313","https://openalex.org/W2038666705","https://openalex.org/W2046830558","https://openalex.org/W2051978688","https://openalex.org/W2054633247","https://openalex.org/W2059072625","https://openalex.org/W2061019658","https://openalex.org/W2062937278","https://openalex.org/W2065849599","https://openalex.org/W2068816944","https://openalex.org/W2072858195","https://openalex.org/W2073767361","https://openalex.org/W2080406045","https://openalex.org/W2099007680","https://openalex.org/W2099677903","https://openalex.org/W2100310618","https://openalex.org/W2100945416","https://openalex.org/W2105776892","https://openalex.org/W2107643286","https://openalex.org/W2110155099","https://openalex.org/W2110762996","https://openalex.org/W2120999344","https://openalex.org/W2123475055","https://openalex.org/W2128666163","https://openalex.org/W2132887549","https://openalex.org/W2133766618","https://openalex.org/W2135198476","https://openalex.org/W2135569498","https://openalex.org/W2136706100","https://openalex.org/W2139092060","https://openalex.org/W2139164805","https://openalex.org/W2141051748","https://openalex.org/W2142481192","https://openalex.org/W2142871322","https://openalex.org/W2146338950","https://openalex.org/W2147105902","https://openalex.org/W2149014999","https://openalex.org/W2149783794","https://openalex.org/W2151553346","https://openalex.org/W2157353183","https://openalex.org/W2158026923","https://openalex.org/W2158744032","https://openalex.org/W2160988203","https://openalex.org/W2163732854","https://openalex.org/W2163956676","https://openalex.org/W2164519300","https://openalex.org/W2164636917","https://openalex.org/W2168571614","https://openalex.org/W2171868993","https://openalex.org/W2172232422","https://openalex.org/W2188116548","https://openalex.org/W2285020383","https://openalex.org/W2317739826","https://openalex.org/W2327194587","https://openalex.org/W2367798545","https://openalex.org/W2408181256","https://openalex.org/W2911964244","https://openalex.org/W3141989311","https://openalex.org/W3149100806","https://openalex.org/W4205170104","https://openalex.org/W4234263644","https://openalex.org/W4238859253","https://openalex.org/W4243379839","https://openalex.org/W4285719527","https://openalex.org/W4298982457","https://openalex.org/W4399585247","https://openalex.org/W6674712254","https://openalex.org/W6676396137","https://openalex.org/W6680366005","https://openalex.org/W6687173432"],"related_works":["https://openalex.org/W2137153556","https://openalex.org/W2142526507","https://openalex.org/W2110715265","https://openalex.org/W1580733868","https://openalex.org/W2545585904","https://openalex.org/W755676069","https://openalex.org/W2054811852","https://openalex.org/W2754335648","https://openalex.org/W2295348316","https://openalex.org/W2791411508"],"abstract_inverted_index":{"Defect":[0],"prediction":[1,19,153,337,368],"models":[2,196,257,301,338,369],"help":[3],"software":[4,37,70],"organizations":[5],"to":[6,74,145,197,258,285,319,343,347],"anticipate":[7],"where":[8],"defects":[9],"will":[10],"appear":[11],"in":[12,64,115,133,213,228,247],"the":[13,40,45,52,62,66,85,88,94,104,134,185,190,203,207,214,218,224,232,239,244,251,267,273,283,286,292,306,320,326,333,350,355],"future.":[14],"When":[15],"training":[16],"a":[17,28,82,372],"defect":[18,22,137,152,191,199,260,304,336,367],"model,":[20],"historical":[21],"data":[23,163],"is":[24,84],"often":[25,49,76,290,340],"mined":[26],"from":[27,165],"Version":[29],"Control":[30],"System":[31],"(VCS,":[32],"e.g.,":[33],"Subversion),":[34],"which":[35],"records":[36],"changes":[38],"at":[39,51],"file-level.":[41],"Software":[42],"metrics,":[43,181],"on":[44],"other":[46,122,293,327],"hand,":[47],"are":[48,72,120,316,339],"calculated":[50],"class-":[53,67],"or":[54,262,269,308],"method-level":[55,69],"(e.g.,":[56,125],"McCabe's":[57],"Cyclomatic":[58],"Complexity).":[59],"To":[60],"address":[61],"disagreement":[63],"granularity,":[65],"and":[68,111,189,297],"metrics":[71,188],"aggregated":[73],"file-level,":[75],"using":[77,162],"summation":[78,101,204,268,351],"(i.e.,":[79,206],"McCabe":[80,89],"of":[81,87,90,108,136,158,231,238,250,272,325,335,358,374],"file":[83],"sum":[86],"all":[91,237,271],"methods":[92],"within":[93],"file).":[95],"A":[96],"recent":[97],"study":[98],"shows":[99],"that":[100,315,365],"significantly":[102,177,317],"inflates":[103],"correlation":[105],"between":[106,187],"lines":[107],"code":[109],"(Sloc)":[110],"cyclomatic":[112],"complexity":[113],"(Cc)":[114],"Java":[116],"projects.":[117],"While":[118],"there":[119],"many":[121],"aggregation":[123,149,160,174,211,241,275,295,310,329,352,361,375],"schemes":[124,150,161,175,242,276,311],"central":[126],"tendency,":[127],"dispersion),":[128],"they":[129],"have":[130],"remained":[131],"unexplored":[132],"scope":[135],"prediction.":[138],"In":[139],"this":[140],"study,":[141],"we":[142,170,363],"set":[143],"out":[144],"investigate":[146],"how":[147],"different":[148],"impact":[151],"models.":[154],"Through":[155],"an":[156],"analysis":[157],"11":[159,229],"collected":[164],"255":[166],"open":[167],"source":[168],"projects,":[169,234],"find":[171],"that:":[172],"(1)":[173],"can":[176],"alter":[178],"correlations":[179,186],"among":[180,223],"as":[182,184],"well":[183],"count;":[192],"(2)":[193],"when":[194,255,299],"constructing":[195,256,300],"predict":[198,259],"proneness,":[200],"applying":[201,236,265,270,359],"only":[202,216,266,348],"scheme":[205,212],"most":[208],"commonly":[209],"used":[210],"literature)":[215],"achieves":[217,243,277],"best":[219,222,245,287,321],"performance":[220,246,288,313,322,334],"(the":[221],"12":[225],"studied":[226,233,240,252,274,294,328],"configurations)":[227],"percent":[230,249],"while":[235],"40":[248],"projects;":[253],"(3)":[254],"rank":[261],"count,":[263],"either":[264],"similar":[278],"performance,":[279],"with":[280],"both":[281],"achieving":[282],"closest":[284],"more":[289],"than":[291,323],"schemes;":[296],"(4)":[298],"for":[302],"effort-aware":[303],"prediction,":[305],"mean":[307],"median":[309],"yield":[312],"values":[314],"closer":[318],"any":[324],"schemes.":[330,376],"Broadly":[331],"speaking,":[332],"underestimated":[341],"due":[342],"our":[344],"community's":[345],"tendency":[346],"use":[349],"scheme.":[353],"Given":[354],"potential":[356],"benefit":[357],"additional":[360],"schemes,":[362],"advise":[364],"future":[366],"should":[370],"explore":[371],"variety":[373]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}