{"id":"https://openalex.org/W4313142332","doi":"https://doi.org/10.1109/tse.2022.3220740","title":"A Comprehensive Investigation of the Impact of Class Overlap on Software Defect Prediction","display_name":"A Comprehensive Investigation of the Impact of Class Overlap on Software Defect Prediction","publication_year":2022,"publication_date":"2022-11-09","ids":{"openalex":"https://openalex.org/W4313142332","doi":"https://doi.org/10.1109/tse.2022.3220740"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2022.3220740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3220740","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/A5027202117","display_name":"Lina Gong","orcid":"https://orcid.org/0000-0002-5272-6706"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Gong","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-5272-6706","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100765845","display_name":"Haoxiang Zhang","orcid":"https://orcid.org/0000-0002-3921-1724"},"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":"Haoxiang Zhang","raw_affiliation_strings":["Software Analysis and Intelligence Lab (SAIL), School of Computing, Queen's University, Kingston, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3921-1724","affiliations":[{"raw_affiliation_string":"Software Analysis and Intelligence Lab (SAIL), School of Computing, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005439960","display_name":"Jingxuan Zhang","orcid":"https://orcid.org/0000-0002-8437-6640"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxuan Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-8437-6640","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051555459","display_name":"Mingqiang Wei","orcid":"https://orcid.org/0000-0003-0429-490X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqiang Wei","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-0429-490X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025184050","display_name":"Zhiqiu Huang","orcid":"https://orcid.org/0000-0001-6843-1892"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiu Huang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0001-6843-1892","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.5312,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9835116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"49","issue":"4","first_page":"2440","last_page":"2458"},"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":0.998199999332428,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9883000254631042,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8368166089057922},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6282007098197937},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5676480531692505},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5550763010978699},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5180673599243164},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.51583331823349},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49042007327079773},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.47773975133895874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46439439058303833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10009986162185669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368166089057922},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6282007098197937},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5676480531692505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5550763010978699},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5180673599243164},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.51583331823349},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49042007327079773},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.47773975133895874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46439439058303833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10009986162185669},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2022.3220740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3220740","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":[],"awards":[{"id":"https://openalex.org/G437908683","display_name":null,"funder_award_id":"BK20220881","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7809263010","display_name":null,"funder_award_id":"62202223","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W102369970","https://openalex.org/W150336312","https://openalex.org/W168970045","https://openalex.org/W420228460","https://openalex.org/W752888290","https://openalex.org/W1541033774","https://openalex.org/W1561613409","https://openalex.org/W1565746575","https://openalex.org/W1596515083","https://openalex.org/W1887734902","https://openalex.org/W1971654961","https://openalex.org/W1974601952","https://openalex.org/W1975040830","https://openalex.org/W1982105191","https://openalex.org/W1989354793","https://openalex.org/W2042699031","https://openalex.org/W2045116160","https://openalex.org/W2046830558","https://openalex.org/W2048456683","https://openalex.org/W2069395014","https://openalex.org/W2073294644","https://openalex.org/W2097883090","https://openalex.org/W2099919734","https://openalex.org/W2101227285","https://openalex.org/W2102636708","https://openalex.org/W2105776892","https://openalex.org/W2110065044","https://openalex.org/W2112658968","https://openalex.org/W2118283821","https://openalex.org/W2125847307","https://openalex.org/W2126326838","https://openalex.org/W2132887549","https://openalex.org/W2135198476","https://openalex.org/W2142481192","https://openalex.org/W2146338950","https://openalex.org/W2147386665","https://openalex.org/W2148143831","https://openalex.org/W2149014999","https://openalex.org/W2151666086","https://openalex.org/W2156571267","https://openalex.org/W2158744032","https://openalex.org/W2172232422","https://openalex.org/W2242800359","https://openalex.org/W2276400542","https://openalex.org/W2281037394","https://openalex.org/W2367798545","https://openalex.org/W2474835145","https://openalex.org/W2476682851","https://openalex.org/W2510620627","https://openalex.org/W2516809705","https://openalex.org/W2523268328","https://openalex.org/W2548915941","https://openalex.org/W2587676558","https://openalex.org/W2599212561","https://openalex.org/W2729440153","https://openalex.org/W2731935965","https://openalex.org/W2735995639","https://openalex.org/W2766521509","https://openalex.org/W2783908707","https://openalex.org/W2795013017","https://openalex.org/W2805001156","https://openalex.org/W2867335562","https://openalex.org/W2909172538","https://openalex.org/W2954276596","https://openalex.org/W2963520355","https://openalex.org/W2963548617","https://openalex.org/W2981328759","https://openalex.org/W2999752750","https://openalex.org/W3013745307","https://openalex.org/W3034708533","https://openalex.org/W3109072952","https://openalex.org/W3127971289","https://openalex.org/W3163556840","https://openalex.org/W4243562335","https://openalex.org/W4245807786","https://openalex.org/W4250023757","https://openalex.org/W4399549220","https://openalex.org/W6667962631","https://openalex.org/W6682904970","https://openalex.org/W6712312853","https://openalex.org/W6713589489"],"related_works":["https://openalex.org/W2112835755","https://openalex.org/W4291951920","https://openalex.org/W2349674371","https://openalex.org/W2898732673","https://openalex.org/W2097495471","https://openalex.org/W1696545756","https://openalex.org/W2952827811","https://openalex.org/W2056202066","https://openalex.org/W2963262648","https://openalex.org/W4301867002"],"abstract_inverted_index":{"Software":[0],"Defect":[1],"Prediction":[2],"(SDP)":[3],"is":[4],"one":[5],"of":[6,23,39,41,52,65,72,93,116,125,141,160,169,178,187,192,218,244],"the":[7,15,21,27,45,50,63,70,91,109,113,123,136,139,176,185,188,196,200,216,241],"most":[8],"vital":[9],"and":[10,32,128,138,203],"cost-efficient":[11],"operations":[12],"to":[13,61,88,239],"ensure":[14],"software":[16],"quality.":[17],"However,":[18],"there":[19],"exists":[20],"phenomenon":[22],"class":[24,94,110,126,170,182],"overlap":[25,95,127,171,183,209,227,242],"in":[26,37,112],"SDP":[28,53,144,161,179,193,219,248],"datasets":[29,162,223,245],"(i.e.,":[30],"defective":[31],"non-defective":[33],"modules":[34],"are":[35,77],"similar":[36],"terms":[38],"values":[40],"metrics),":[42],"which":[43],"hinders":[44],"performance":[46,71,137,177,217],"as":[47,49],"well":[48],"use":[51],"models.":[54,145,249],"Even":[55],"though":[56],"efforts":[57],"have":[58,172],"been":[59],"made":[60],"investigate":[62,90,122],"impact":[64,92,124],"removing":[66],"overlapping":[67,103,131,164],"technique":[68],"on":[69,96,135,151,175,222],"SDP,":[73],"many":[74],"open":[75],"issues":[76],"still":[78],"challenging":[79],"yet":[80],"unknown.":[81],"Therefore,":[82],"we":[83,99,155],"conduct":[84],"an":[85,102,147],"empirical":[86],"study":[87,150],"comprehensively":[89],"SDP.":[97],"Specifically,":[98],"first":[100],"propose":[101],"instances":[104],"identification":[105],"approach":[106],"by":[107],"analyzing":[108],"distribution":[111],"local":[114],"neighborhood":[115],"a":[117],"given":[118],"instance.":[119],"We":[120,229],"then":[121],"two":[129],"common":[130],"instance":[132],"handling":[133,210],"techniques":[134,211],"interpretation":[140],"seven":[142],"representative":[143],"Through":[146],"extensive":[148],"case":[149],"230":[152],"diversity":[153],"datasets,":[154],"observe":[156],"that:":[157],"i)":[158],"70.0%":[159],"contain":[163],"instances;":[165],"ii)":[166],"different":[167,173],"levels":[168],"impacts":[174],"models;":[180],"iii)":[181],"affects":[184],"rank":[186],"important":[189],"feature":[190,197],"list":[191],"models,":[194],"particularly":[195],"lists":[198],"at":[199],"top":[201,204],"2":[202],"3":[205],"ranks;":[206],"IV)":[207],"Class":[208],"could":[212],"statistically":[213],"significantly":[214],"improve":[215],"models":[220],"trained":[221],"with":[224],"over":[225],"12.5%":[226],"ratios.":[228],"suggest":[230],"that":[231],"future":[232],"work":[233],"should":[234],"apply":[235],"our":[236],"KNN":[237],"method":[238],"identify":[240],"ratios":[243],"before":[246],"building":[247]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}