{"id":"https://openalex.org/W2805001156","doi":"https://doi.org/10.1109/tse.2018.2836442","title":"A Comprehensive Investigation of the Role of Imbalanced Learning for Software Defect Prediction","display_name":"A Comprehensive Investigation of the Role of Imbalanced Learning for Software Defect Prediction","publication_year":2018,"publication_date":"2018-05-15","ids":{"openalex":"https://openalex.org/W2805001156","doi":"https://doi.org/10.1109/tse.2018.2836442","mag":"2805001156"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2018.2836442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2018.2836442","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":true,"oa_status":"green","oa_url":"http://bura.brunel.ac.uk/bitstream/2438/16318/4/FullText.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101514255","display_name":"Xiaoyan Song","orcid":"https://orcid.org/0000-0002-4907-0566"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4391768271","display_name":"State Key Laboratory of Software Engineering","ror":"https://ror.org/01z3jn402","country_code":null,"type":"facility","lineage":["https://openalex.org/I37461747","https://openalex.org/I4391768271"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinbao Song","raw_affiliation_strings":["Department of Computer Science & Technology, Xi'an Jiaotong University, Xi'an, China","State Key Laboratory of Software Engineering, Wuhan University, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"State Key Laboratory of Software Engineering, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4391768271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640369","display_name":"Yuchen Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Guo","raw_affiliation_strings":["Department of Computer Science & Technology, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027684680","display_name":"Martin Shepperd","orcid":"https://orcid.org/0000-0003-1874-6145"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Shepperd","raw_affiliation_strings":["Department of Computer Science, Brunel University, Uxbridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brunel University, Uxbridge, United Kingdom","institution_ids":["https://openalex.org/I59433898"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101514255"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4391768271","https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":46.4626,"has_fulltext":true,"cited_by_count":286,"citation_normalized_percentile":{"value":0.99789188,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"45","issue":"12","first_page":"1253","last_page":"1269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9879999756813049,"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":0.8094284534454346},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7631958723068237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7314770817756653},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6128071546554565},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.45529890060424805},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.45256689190864563},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.4420095682144165},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4157012701034546},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33425575494766235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10314813256263733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8094284534454346},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7631958723068237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7314770817756653},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6128071546554565},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45529890060424805},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.45256689190864563},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.4420095682144165},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4157012701034546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33425575494766235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10314813256263733},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tse.2018.2836442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2018.2836442","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:bura.brunel.ac.uk:2438/16318","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/16318","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/16318/4/FullText.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:bura.brunel.ac.uk:2438/16318","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/16318","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/16318/4/FullText.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1679237078","display_name":null,"funder_award_id":"61373046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2636002203","display_name":null,"funder_award_id":"61210004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3758571350","display_name":null,"funder_award_id":"1210004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324766","display_name":"Brunel University London","ror":"https://ror.org/00dn4t376"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2805001156.pdf"},"referenced_works_count":103,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W142191673","https://openalex.org/W146100937","https://openalex.org/W165633843","https://openalex.org/W168970045","https://openalex.org/W578092267","https://openalex.org/W1524761913","https://openalex.org/W1563938718","https://openalex.org/W1596515083","https://openalex.org/W1670263352","https://openalex.org/W1978813754","https://openalex.org/W1980851144","https://openalex.org/W1981399499","https://openalex.org/W1984712439","https://openalex.org/W1988790447","https://openalex.org/W1993220166","https://openalex.org/W2008596407","https://openalex.org/W2015452969","https://openalex.org/W2026750231","https://openalex.org/W2029123435","https://openalex.org/W2032435122","https://openalex.org/W2033418259","https://openalex.org/W2040181375","https://openalex.org/W2043837581","https://openalex.org/W2043852022","https://openalex.org/W2049831820","https://openalex.org/W2050496630","https://openalex.org/W2053724458","https://openalex.org/W2056601071","https://openalex.org/W2058591750","https://openalex.org/W2058732827","https://openalex.org/W2068430427","https://openalex.org/W2073294644","https://openalex.org/W2096945460","https://openalex.org/W2097883090","https://openalex.org/W2099454382","https://openalex.org/W2099919734","https://openalex.org/W2100208452","https://openalex.org/W2100310618","https://openalex.org/W2103715428","https://openalex.org/W2107432340","https://openalex.org/W2107498895","https://openalex.org/W2113599721","https://openalex.org/W2114531539","https://openalex.org/W2118283821","https://openalex.org/W2118978333","https://openalex.org/W2119016061","https://openalex.org/W2120457925","https://openalex.org/W2125999269","https://openalex.org/W2127623179","https://openalex.org/W2128939007","https://openalex.org/W2130883460","https://openalex.org/W2130898128","https://openalex.org/W2132318217","https://openalex.org/W2132887549","https://openalex.org/W2133990480","https://openalex.org/W2135198476","https://openalex.org/W2135874888","https://openalex.org/W2136256517","https://openalex.org/W2137235241","https://openalex.org/W2137959503","https://openalex.org/W2139393465","https://openalex.org/W2142481192","https://openalex.org/W2142827986","https://openalex.org/W2145026116","https://openalex.org/W2146338950","https://openalex.org/W2147169507","https://openalex.org/W2147386665","https://openalex.org/W2148143831","https://openalex.org/W2151666086","https://openalex.org/W2153054327","https://openalex.org/W2154062297","https://openalex.org/W2158275940","https://openalex.org/W2158698691","https://openalex.org/W2158864412","https://openalex.org/W2160988203","https://openalex.org/W2163837601","https://openalex.org/W2164330572","https://openalex.org/W2171824022","https://openalex.org/W2172032660","https://openalex.org/W2196215201","https://openalex.org/W2297432279","https://openalex.org/W2319561871","https://openalex.org/W2321650456","https://openalex.org/W2360967250","https://openalex.org/W2385483600","https://openalex.org/W2490420619","https://openalex.org/W2504945316","https://openalex.org/W2535333834","https://openalex.org/W2536062280","https://openalex.org/W2912934387","https://openalex.org/W3122359843","https://openalex.org/W3209742063","https://openalex.org/W4206600618","https://openalex.org/W4212883601","https://openalex.org/W4244238212","https://openalex.org/W4249777822","https://openalex.org/W4250023757","https://openalex.org/W6602002561","https://openalex.org/W6605896687","https://openalex.org/W6631546530","https://openalex.org/W6680919041","https://openalex.org/W6687403153"],"related_works":["https://openalex.org/W3203175338","https://openalex.org/W2356901839","https://openalex.org/W3209501579","https://openalex.org/W2497114785","https://openalex.org/W2969547062","https://openalex.org/W4283162910","https://openalex.org/W2803806723","https://openalex.org/W4245578471","https://openalex.org/W4250833027","https://openalex.org/W119609074"],"abstract_inverted_index":{"Context:":[0],"Software":[1],"defect":[2],"prediction":[3],"(SDP)":[4],"is":[5,42,167,232,274],"an":[6,134,170],"important":[7],"challenge":[8],"in":[9,260],"the":[10,25,80,87,175,222,236,258,265,281,316,331,339],"field":[11],"of":[12,27,83,89,101,122,140,192,203,218,224,252,271,280,283,319,342],"software":[13],"engineering,":[14],"hence":[15],"much":[16],"research":[17],"work":[18],"has":[19,60,254],"been":[20,62],"conducted,":[21],"most":[22,255],"notably":[23],"through":[24],"use":[26],"machine":[28],"learning":[29,52,91,109,128,148,226,231,267,302,333,344],"algorithms.":[30,149],"However,":[31],"class-imbalance":[32],"typified":[33],"by":[34,64,264],"few":[35],"defective":[36],"components":[37],"and":[38,59,92,106,125,145,180,286,322],"many":[39],"non-defective":[40],"ones":[41],"a":[43,74,187,289],"common":[44],"occurrence":[45],"causing":[46],"difficulties":[47],"for":[48,227,307,335],"these":[49,143],"methods.":[50],"Imbalanced":[51,284],"aims":[53],"to":[54,77,325,329],"deal":[55],"with":[56,68,95,239],"this":[57,84],"problem":[58,334],"recently":[61],"deployed":[63],"some":[65],"researchers,":[66],"unfortunately":[67],"inconsistent":[69],"results.":[70,161],"Objective:":[71],"We":[72,112],"conduct":[73],"comprehensive":[75],"experiment":[76],"explore":[78],"(a)":[79,184],"basic":[81],"characteristics":[82],"problem;":[85],"(b)":[86,212],"effect":[88],"imbalanced":[90,108,127,147,230,266,301,311,320,332,343],"its":[93],"interactions":[94,141],"(i)":[96],"data":[97,116,196,237,313],"imbalance,":[98,243],"(ii)":[99],"type":[100,251],"classifier,":[102],"(iii)":[103],"input":[104,123,272],"metrics":[105,124,273],"(iv)":[107],"method.":[110],"Method:":[111],"systematically":[113],"evaluate":[114],"27":[115,152],"sets,":[117],"7":[118,120,154,156],"classifiers,":[119],"types":[121],"17":[126,158],"methods":[129],"(including":[130],"doing":[131],"nothing)":[132],"using":[133],"experimental":[135],"design":[136],"that":[137],"enables":[138],"exploration":[139],"between":[142],"factors":[144],"individual":[146],"This":[150,294],"yields":[151],"\u00d7":[153,155,157],"=":[159,210],"22491":[160],"The":[162],"Matthews":[163],"correlation":[164],"coefficient":[165],"(MCC)":[166],"used":[168,178],"as":[169],"unbiased":[171],"performance":[172,223,262],"measure":[173],"(unlike":[174],"more":[176,233],"widely":[177],"F1":[179],"AUC":[181],"measures).":[182],"Results:":[183],"we":[185],"found":[186],"large":[188],"majority":[189],"(87":[190],"percent)":[191],"106":[193],"public":[194],"domain":[195],"sets":[197,238],"exhibit":[198],"moderate":[199,240,308],"or":[200,241,309],"low":[201,216],"level":[202],"imbalance":[204,219],"(imbalance":[205],"ratio":[206],"<;":[207],"10;":[208],"median":[209],"3.94);":[211],"anything":[213],"other":[214],"than":[215],"levels":[217],"clearly":[220],"harm":[221],"traditional":[225],"SDP;":[228],"(c)":[229],"effective":[234],"on":[235,257],"higher":[242],"however":[244],"negative":[245],"results":[246],"are":[247],"always":[248],"possible;":[249],"(d)":[250],"classifier":[253,323],"impact":[256],"improvement":[259],"classification":[261],"followed":[263],"method":[268,321],"itself.":[269],"Type":[270],"not":[275],"influential.":[276],"(e)":[277],"only":[278,304],"52%":[279],"combinations":[282],"Learner":[285],"Classifier":[287],"have":[288],"significant":[290],"positive":[291],"effect.":[292],"Conclusion:":[293],"paper":[295],"offers":[296],"two":[297],"practical":[298],"guidelines.":[299],"First,":[300],"should":[303],"be":[305,326,346],"considered":[306],"highly":[310],"SDP":[312],"sets.":[314],"Second,":[315],"appropriate":[317],"combination":[318],"needs":[324],"carefully":[327],"chosen":[328],"ameliorate":[330],"SDP.":[336],"In":[337],"contrast,":[338],"indiscriminate":[340],"application":[341],"can":[345],"harmful.":[347]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":54},{"year":2021,"cited_by_count":53},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}