{"id":"https://openalex.org/W4389374085","doi":"https://doi.org/10.1145/3628797.3628963","title":"On the Value of Code Embedding and Imbalanced Learning Approaches for Software Defect Prediction","display_name":"On the Value of Code Embedding and Imbalanced Learning Approaches for Software Defect Prediction","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389374085","doi":"https://doi.org/10.1145/3628797.3628963"},"language":"en","primary_location":{"id":"doi:10.1145/3628797.3628963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3628963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-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/A5021818134","display_name":"Anh M. T. Bui","orcid":"https://orcid.org/0000-0001-7877-9438"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Bui Thi-Mai-Anh","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062511145","display_name":"Nguy\u1ec5n Nh\u1ea5t H\u1ea3i","orcid":"https://orcid.org/0000-0002-7724-3612"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Nhat-Hai","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021818134"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.4589,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71832664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"510","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955000281333923,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9850999712944031,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8163830637931824},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7736648917198181},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.6092705726623535},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.6042741537094116},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.5747742652893066},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5249921083450317},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48787927627563477},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48182740807533264},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.4612957239151001},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4592426121234894},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44895729422569275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4485352635383606},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44849419593811035},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.35629770159721375},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21966952085494995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163830637931824},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7736648917198181},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.6092705726623535},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.6042741537094116},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.5747742652893066},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5249921083450317},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48787927627563477},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48182740807533264},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.4612957239151001},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4592426121234894},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44895729422569275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4485352635383606},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44849419593811035},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.35629770159721375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21966952085494995},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3628797.3628963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3628963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W76990466","https://openalex.org/W1964062576","https://openalex.org/W1964962870","https://openalex.org/W1994410331","https://openalex.org/W2072785870","https://openalex.org/W2090854192","https://openalex.org/W2097883090","https://openalex.org/W2100945416","https://openalex.org/W2107686700","https://openalex.org/W2132791018","https://openalex.org/W2137029138","https://openalex.org/W2148143831","https://openalex.org/W2158864412","https://openalex.org/W2360967250","https://openalex.org/W2542146196","https://openalex.org/W2743316948","https://openalex.org/W2796991982","https://openalex.org/W2805001156","https://openalex.org/W2808896747","https://openalex.org/W2897049944","https://openalex.org/W2945699300","https://openalex.org/W2964110017","https://openalex.org/W2998581331","https://openalex.org/W3164087770","https://openalex.org/W3198685994","https://openalex.org/W4250023757","https://openalex.org/W4293764002","https://openalex.org/W4310113640"],"related_works":["https://openalex.org/W377327559","https://openalex.org/W4210653322","https://openalex.org/W2078744341","https://openalex.org/W119580281","https://openalex.org/W4206152185","https://openalex.org/W2969257295","https://openalex.org/W1976804602","https://openalex.org/W4245904369","https://openalex.org/W3006945192","https://openalex.org/W3049398420"],"abstract_inverted_index":{"Automated":[0],"software":[1,14,21,30,74],"defect":[2,31,158],"prediction":[3,32],"aims":[4],"to":[5,19,103,154],"identify":[6],"and":[7,44,60,144],"estimate":[8],"the":[9,49,64,77,96,131,156,164,174,185],"likelihood":[10,116],"of":[11,51,66,80,98,117,133,166,188],"defects":[12],"in":[13,90],"source":[15,41,81,99,119,141,196],"code":[16,42,82,100,142],"elements,":[17],"seeking":[18],"enhance":[20],"quality":[22],"while":[23],"reducing":[24],"testing":[25],"costs.":[26],"Previous":[27],"research":[28],"on":[29,35,72,173],"primarily":[33],"concentrated":[34],"investigating":[36],"design-related":[37,145],"features":[38,143],"such":[39],"as":[40,191],"complexity":[43],"object-oriented":[45],"design":[46],"metrics":[47],"for":[48],"purpose":[50],"classifying":[52],"program":[53,108],"elements":[54,109],"into":[55],"two":[56],"categories:":[57],"(i)":[58],"defective":[59,127,195],"(ii)":[61],"non-detective.":[62],"Nevertheless,":[63],"majority":[65],"these":[67],"studies":[68],"have":[69],"relied":[70],"solely":[71],"hand-crafted":[73],"metrics,":[75],"neglecting":[76],"valuable":[78],"asset":[79],"instruction,":[83],"which":[84],"can":[85],"play":[86],"a":[87,111,118,134],"pivotal":[88],"role":[89],"detecting":[91],"bugs.":[92],"This":[93],"study":[94],"leverages":[95],"use":[97],"embedding":[101],"techniques":[102],"extract":[104],"essential":[105],"information":[106],"from":[107],"through":[110,130],"convolutional":[112],"neural":[113],"network.":[114],"The":[115,180],"file":[120],"element":[121],"(e.g.,":[122],"class":[123],"or":[124],"method)":[125],"being":[126],"is":[128],"established":[129],"utilization":[132],"fully":[135],"connected":[136],"network":[137],"that":[138],"incorporates":[139],"both":[140],"attributes.":[146],"Additionally,":[147],"we":[148,170],"explore":[149],"specific":[150],"imbalanced":[151],"learning":[152],"strategies":[153],"address":[155],"skewed":[157],"data":[159],"distribution":[160],"issue.":[161],"To":[162],"assess":[163],"effectiveness":[165],"our":[167,189],"proposed":[168],"approach,":[169],"conducted":[171],"experiments":[172],"publicly":[175],"available":[176],"dataset,":[177],"namely":[178],"PROMISE.":[179],"empirical":[181],"results":[182],"consistently":[183],"showcase":[184],"superior":[186],"performance":[187],"method,":[190],"it":[192],"effectively":[193],"predicts":[194],"files,":[197],"outperforming":[198],"other":[199],"state-of-the-art":[200],"models.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
