{"id":"https://openalex.org/W3209257685","doi":"https://doi.org/10.1109/tr.2021.3118026","title":"A Comparative Study of Class Rebalancing Methods for Security Bug Report Classification","display_name":"A Comparative Study of Class Rebalancing Methods for Security Bug Report Classification","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3209257685","doi":"https://doi.org/10.1109/tr.2021.3118026","mag":"3209257685"},"language":"en","primary_location":{"id":"doi:10.1109/tr.2021.3118026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2021.3118026","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Reliability","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/A5061098741","display_name":"Wei Zheng","orcid":"https://orcid.org/0000-0001-7969-1630"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zheng","raw_affiliation_strings":["National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, MIIT Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Xi\u2019an, China","National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, MIIT Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7969-1630","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, MIIT Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, MIIT Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057728039","display_name":"Yuxing Xun","orcid":"https://orcid.org/0000-0002-3409-934X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Xun","raw_affiliation_strings":["School of Software, Northwestern Polytechnical University, Xi\u2019an, China","School of Software, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-3409-934X","affiliations":[{"raw_affiliation_string":"School of Software, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Software, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035031650","display_name":"Xiaoxue Wu","orcid":"https://orcid.org/0000-0002-7567-3643"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxue Wu","raw_affiliation_strings":["College of Information Engineering (College of Artificial Intelligence), Yangzhou University, Yangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7567-3643","affiliations":[{"raw_affiliation_string":"College of Information Engineering (College of Artificial Intelligence), Yangzhou University, Yangzhou, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016513676","display_name":"Zhi Deng","orcid":"https://orcid.org/0000-0003-4813-5265"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Deng","raw_affiliation_strings":["School of Computer Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441911","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0002-1180-3891"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["School of Information Science and Technology, Nantong University, Nantong, China"],"raw_orcid":"https://orcid.org/0000-0002-1180-3891","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053058502","display_name":"Yulei Sui","orcid":"https://orcid.org/0000-0002-9510-6574"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yulei Sui","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.8327,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.99481911,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"70","issue":"4","first_page":"1658","last_page":"1670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9980999827384949,"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":0.9980999827384949,"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":0.991599977016449,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/class","display_name":"Class (philosophy)","score":0.6722820997238159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6569007635116577},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.6167593002319336},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5415769815444946},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5400941371917725},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4976802170276642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47950488328933716},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.4370405972003937},{"id":"https://openalex.org/keywords/software-regression","display_name":"Software regression","score":0.4250250458717346},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4245555102825165},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4144488573074341},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.19374749064445496},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1867162585258484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17116940021514893},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.13900551199913025}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6722820997238159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6569007635116577},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.6167593002319336},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5415769815444946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5400941371917725},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4976802170276642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47950488328933716},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4370405972003937},{"id":"https://openalex.org/C191727507","wikidata":"https://www.wikidata.org/wiki/Q24346","display_name":"Software regression","level":5,"score":0.4250250458717346},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4245555102825165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4144488573074341},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.19374749064445496},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1867162585258484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17116940021514893},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.13900551199913025},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tr.2021.3118026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2021.3118026","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Reliability","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1964940342","https://openalex.org/W2081461908","https://openalex.org/W2101726875","https://openalex.org/W2104933073","https://openalex.org/W2123493477","https://openalex.org/W2132791018","https://openalex.org/W2474835145","https://openalex.org/W2492513888","https://openalex.org/W2570487166","https://openalex.org/W2589805776","https://openalex.org/W2624745934","https://openalex.org/W2744611928","https://openalex.org/W2781021471","https://openalex.org/W2782726450","https://openalex.org/W2795013017","https://openalex.org/W2808595449","https://openalex.org/W2886714101","https://openalex.org/W2887004133","https://openalex.org/W2896206046","https://openalex.org/W2911964244","https://openalex.org/W2915008153","https://openalex.org/W2918408501","https://openalex.org/W2919824040","https://openalex.org/W2925522637","https://openalex.org/W2942889063","https://openalex.org/W2946143226","https://openalex.org/W2953675148","https://openalex.org/W2962981269","https://openalex.org/W2963548617","https://openalex.org/W2966158888","https://openalex.org/W2970433196","https://openalex.org/W2984385475","https://openalex.org/W2989219518","https://openalex.org/W2999309192","https://openalex.org/W3015200424","https://openalex.org/W3036035276","https://openalex.org/W3047060354","https://openalex.org/W3134770171","https://openalex.org/W3190752170","https://openalex.org/W3194977131","https://openalex.org/W3197715376","https://openalex.org/W4234367654","https://openalex.org/W4236586490","https://openalex.org/W4239510810","https://openalex.org/W4242400040","https://openalex.org/W4245807786","https://openalex.org/W4388297464","https://openalex.org/W6675634716","https://openalex.org/W6739444879","https://openalex.org/W6760658752","https://openalex.org/W6763203725"],"related_works":["https://openalex.org/W3009111612","https://openalex.org/W2044225531","https://openalex.org/W2597543511","https://openalex.org/W2901462014","https://openalex.org/W3045036521","https://openalex.org/W3004570974","https://openalex.org/W2135303064","https://openalex.org/W3185667871","https://openalex.org/W2603381882","https://openalex.org/W2022585969"],"abstract_inverted_index":{"Identifying":[0],"security":[1,15],"bug":[2,8,60],"reports":[3,61],"(SBRs)":[4],"accurately":[5],"from":[6],"a":[7,12,92],"repository":[9],"can":[10,122,145,183],"reduce":[11],"software":[13],"product\u2019s":[14],"risk.":[16],"However,":[17],"the":[18,27,71,74,113,118,124,131,135,138,147,150,155,160],"class":[19,75,98,119,189],"imbalance":[20,76],"problem":[21],"exists":[22],"for":[23,107,186,194],"SBR":[24,79,108,195],"prediction":[25,80,87,196],"since":[26],"number":[28],"of":[29,53,73,95,128,137],"SBRs":[30],"is":[31],"often":[32],"limited,":[33],"and":[34,81,140,163,192],"this":[35],"issue":[36,77],"has":[37],"not":[38],"been":[39],"thoroughly":[40],"investigated":[41],"in":[42,62,126,130,159,167,197],"previous":[43],"studies.":[44],"In":[45],"our":[46,65,178],"study,":[47],"we":[48,90,171],"choose":[49],"six":[50,96],"real-world":[51],"projects":[52],"different":[54],"sizes":[55],"with":[56,102,112,149],"over":[57],"120":[58],"000":[59],"total":[63],"as":[64],"empirical":[66,179],"subjects.":[67],"We":[68],"first":[69],"analyze":[70],"impact":[72,85],"on":[78,86,165,177],"confirm":[82],"its":[83],"negative":[84],"performance.":[88],"Then":[89],"perform":[91],"comparative":[93],"study":[94],"state-of-the-art":[97],"rebalancing":[99,120,190],"methods":[100,121,191],"combined":[101],"five":[103],"popular":[104],"classification":[105,143],"algorithms":[106],"prediction.":[109],"By":[110],"comparing":[111],"baseline":[114],"method":[115],"Farsec,":[116],"using":[117],"improve":[123],"performance":[125,156],"78%":[127],"cases":[129],"worst":[132],"case.":[133],"Moreover,":[134],"combination":[136],"Rose":[139],"random":[141],"forest":[142],"algorithm":[144],"construct":[146],"model":[148],"best":[151,161],"performance,":[152],"which":[153,182],"increases":[154],"by":[157],"267%":[158],"case":[162],"75%":[164],"average":[166],"terms":[168],"ofF1-score.":[169],"Finally,":[170],"summarize":[172],"eight":[173],"main":[174],"findings":[175],"based":[176],"studies\u2019":[180],"results,":[181],"provide":[184],"guidelines":[185],"choosing":[187],"appropriate":[188],"classifiers":[193],"practice.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}