{"id":"https://openalex.org/W4406012448","doi":"https://doi.org/10.1109/access.2024.3525069","title":"Leveraging an Enhanced CodeBERT-Based Model for Multiclass Software Defect Prediction via Defect Classification","display_name":"Leveraging an Enhanced CodeBERT-Based Model for Multiclass Software Defect Prediction via Defect Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406012448","doi":"https://doi.org/10.1109/access.2024.3525069"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3525069","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3525069","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3525069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115751068","display_name":"Rida Ghafoor Hussain","orcid":"https://orcid.org/0009-0000-5734-9922"},"institutions":[{"id":"https://openalex.org/I194028371","display_name":"University of Regina","ror":"https://ror.org/03dzc0485","country_code":"CA","type":"education","lineage":["https://openalex.org/I194028371"]},{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["CA","IT"],"is_corresponding":false,"raw_author_name":"Rida Ghafoor Hussain","raw_affiliation_strings":["Department of Information Engineering, University of Florence, Florence, Italy","University of Florence, Italy, Florence, ITALY","Faculty of Engineering and Applied Sciences, University of Regina, Regina, SK, Canada"],"raw_orcid":"https://orcid.org/0009-0000-5734-9922","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"University of Florence, Italy, Florence, ITALY","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Faculty of Engineering and Applied Sciences, University of Regina, Regina, SK, Canada","institution_ids":["https://openalex.org/I194028371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068924885","display_name":"Kin\u2010Choong Yow","orcid":"https://orcid.org/0000-0002-8610-661X"},"institutions":[{"id":"https://openalex.org/I194028371","display_name":"University of Regina","ror":"https://ror.org/03dzc0485","country_code":"CA","type":"education","lineage":["https://openalex.org/I194028371"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kin-Choong Yow","raw_affiliation_strings":["Faculty of Engineering and Applied Sciences, University of Regina, Regina, SK, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8610-661X","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Applied Sciences, University of Regina, Regina, SK, Canada","institution_ids":["https://openalex.org/I194028371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022658803","display_name":"Marco Gori","orcid":"https://orcid.org/0000-0001-6337-5430"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Gori","raw_affiliation_strings":["Department of Information Engineering, University of Siena, Siena, Italy","University of Siena, ITALY, Siena, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]},{"raw_affiliation_string":"University of Siena, ITALY, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":35.2159,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.99670433,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"24383","last_page":"24397"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9958000183105469,"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":0.9739000201225281,"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":0.8323358297348022},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6544702053070068},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.5660930275917053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5451130867004395},{"id":"https://openalex.org/keywords/software-reliability-testing","display_name":"Software reliability testing","score":0.4926753640174866},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.4787004292011261},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43914878368377686},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4309963583946228},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.42790770530700684},{"id":"https://openalex.org/keywords/software-development-process","display_name":"Software development process","score":0.41569802165031433},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41509705781936646},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.40460002422332764},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37304753065109253},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22533974051475525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8323358297348022},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6544702053070068},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.5660930275917053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5451130867004395},{"id":"https://openalex.org/C52928878","wikidata":"https://www.wikidata.org/wiki/Q7554226","display_name":"Software reliability testing","level":5,"score":0.4926753640174866},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.4787004292011261},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43914878368377686},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4309963583946228},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.42790770530700684},{"id":"https://openalex.org/C180152950","wikidata":"https://www.wikidata.org/wiki/Q2904257","display_name":"Software development process","level":4,"score":0.41569802165031433},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41509705781936646},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40460002422332764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37304753065109253},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22533974051475525},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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":2,"locations":[{"id":"doi:10.1109/access.2024.3525069","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3525069","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b4d85971d30a46ab80037d89852f70ba","is_oa":true,"landing_page_url":"https://doaj.org/article/b4d85971d30a46ab80037d89852f70ba","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 24383-24397 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3525069","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3525069","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G427700235","display_name":null,"funder_award_id":"DDG-2024-00035","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320322648","display_name":"Universit\u00e0 degli Studi di Firenze","ror":"https://ror.org/04jr1s763"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2360967250","https://openalex.org/W2592125937","https://openalex.org/W2781491433","https://openalex.org/W2806718802","https://openalex.org/W2895067255","https://openalex.org/W2898762959","https://openalex.org/W2903199829","https://openalex.org/W2914933759","https://openalex.org/W2955354980","https://openalex.org/W2955426500","https://openalex.org/W2964150020","https://openalex.org/W3005773274","https://openalex.org/W3014339000","https://openalex.org/W3030194725","https://openalex.org/W3085192122","https://openalex.org/W3098605233","https://openalex.org/W3106619103","https://openalex.org/W3154474119","https://openalex.org/W3164087770","https://openalex.org/W3174361912","https://openalex.org/W3198912218","https://openalex.org/W4255421341","https://openalex.org/W4285114033","https://openalex.org/W4288777608","https://openalex.org/W4296017095","https://openalex.org/W4297107126","https://openalex.org/W4309628563","https://openalex.org/W4313480230","https://openalex.org/W4328127101","https://openalex.org/W4361009469","https://openalex.org/W4382698864","https://openalex.org/W4388216872","https://openalex.org/W4391165725","https://openalex.org/W4392190394","https://openalex.org/W4394755756","https://openalex.org/W4399208683","https://openalex.org/W4400207882","https://openalex.org/W6745034332","https://openalex.org/W6754601402","https://openalex.org/W6772022830","https://openalex.org/W6779580516","https://openalex.org/W6787895855","https://openalex.org/W6791474232","https://openalex.org/W6800166007"],"related_works":["https://openalex.org/W1521772560","https://openalex.org/W4226182203","https://openalex.org/W4238386252","https://openalex.org/W1494025131","https://openalex.org/W2209071826","https://openalex.org/W2798306226","https://openalex.org/W2051591137","https://openalex.org/W3051764461","https://openalex.org/W2782366913","https://openalex.org/W2054600098"],"abstract_inverted_index":{"Ensuring":[0],"software":[1,13,61,101,179,186,205],"reliability":[2],"through":[3],"early-stage":[4],"defect":[5,62,120,180],"prevention":[6],"and":[7,30,76,92,103,139,158,163,188],"prediction":[8,149],"is":[9,98],"crucial,":[10],"particularly":[11],"as":[12,22,135],"systems":[14],"become":[15],"increasingly":[16],"complex.":[17],"Automated":[18],"testing":[19,102,187],"has":[20],"emerged":[21],"the":[23,170,194,204],"most":[24],"practical":[25],"approach":[26,144],"to":[27,99,125,156],"achieving":[28],"bug-free":[29],"efficient":[31],"code.":[32],"In":[33],"this":[34],"context,":[35],"machine":[36,200],"learning-driven":[37],"methods,":[38],"especially":[39],"those":[40],"leveraging":[41],"natural":[42],"language":[43,174],"models,":[44],"have":[45],"gained":[46],"significant":[47,146],"traction":[48],"for":[49,59,119,178],"developing":[50],"effective":[51],"techniques.":[52,190],"This":[53],"paper":[54],"introduces":[55],"a":[56,81,116],"novel":[57],"framework":[58,114],"automating":[60],"prediction,":[63,121,181],"focusing":[64],"on":[65],"eight":[66,88],"specific":[67],"defects:":[68],"SIGFPE,":[69],"NZEC,":[70],"LOGICAL,":[71],"SYNTAX,":[72],"SIGSEGV,":[73],"SIGABRT,":[74],"SEMANTIC,":[75],"LINKER.":[77],"Our":[78],"research":[79],"involves":[80],"specialized":[82],"dataset":[83],"comprising":[84],"nine":[85],"classes,":[86],"including":[87],"common":[89],"programming":[90],"errors":[91],"one":[93],"error-free":[94],"class.":[95],"The":[96,112],"goal":[97],"enhance":[100],"development":[104,189,206],"processes":[105],"by":[106],"identifying":[107],"defects":[108],"within":[109],"code":[110],"snippets.":[111],"proposed":[113],"utilizes":[115],"CodeBERT-based":[117],"algorithm":[118],"optimizing":[122],"model":[123],"hyperparameters":[124],"achieve":[126],"superior":[127],"accuracy.":[128],"Comparative":[129],"analysis":[130],"against":[131],"established":[132],"models":[133,175,202],"such":[134],"RoBERTa,":[136],"Microsoft":[137],"CodeBERT,":[138],"GPT-2":[140],"demonstrates":[141],"that":[142],"our":[143],"yields":[145],"improvements":[147],"in":[148,161,185],"performance,":[150],"with":[151],"accuracy":[152],"gains":[153],"of":[154,172,197],"up":[155],"20%":[157],"7%":[159],"respectively":[160],"binary":[162],"multi":[164],"class":[165],"experimentation.":[166],"Empirical":[167],"studies":[168],"validate":[169],"effectiveness":[171],"neural":[173],"like":[176],"CodeBERT":[177],"highlighting":[182],"substantial":[183],"advancements":[184],"These":[191],"findings":[192],"underscore":[193],"potential":[195],"benefits":[196],"incorporating":[198],"advanced":[199],"learning":[201],"into":[203],"lifecycle.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}