{"id":"https://openalex.org/W3210208492","doi":"https://doi.org/10.4114/intartif.vol24iss68pp72-88","title":"The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study","display_name":"The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3210208492","doi":"https://doi.org/10.4114/intartif.vol24iss68pp72-88","mag":"3210208492"},"language":"en","primary_location":{"id":"doi:10.4114/intartif.vol24iss68pp72-88","is_oa":true,"landing_page_url":"https://doi.org/10.4114/intartif.vol24iss68pp72-88","pdf_url":null,"source":{"id":"https://openalex.org/S4210203986","display_name":"INTELIGENCIA ARTIFICIAL","issn_l":"1137-3601","issn":["1137-3601","1988-3064"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321681","host_organization_name":"Asociaci\u00f3n Espa\u00f1ola para la Inteligencia Artificial","host_organization_lineage":["https://openalex.org/P4310321681"],"host_organization_lineage_names":["Asociaci\u00f3n Espa\u00f1ola para la Inteligencia Artificial"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Inteligencia Artificial","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4114/intartif.vol24iss68pp72-88","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014589730","display_name":"Mohammad Alshayeb","orcid":"https://orcid.org/0000-0001-7950-0099"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohammad Alshayeb","raw_affiliation_strings":["King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034449159","display_name":"Mashaan Alshammari","orcid":"https://orcid.org/0000-0002-7864-0011"},"institutions":[{"id":"https://openalex.org/I4210088963","display_name":"University of Ha'il","ror":"https://ror.org/013w98a82","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210088963"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mashaan A. Alshammari","raw_affiliation_strings":["University of Ha'il, Ha'il, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ha'il, Ha'il, Saudi Arabia","institution_ids":["https://openalex.org/I4210088963"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8535,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80246229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"24","issue":"68","first_page":"72","last_page":"88"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9950000047683716,"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/support-vector-machine","display_name":"Support vector machine","score":0.7516511678695679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7155090570449829},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6930945515632629},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.673879861831665},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.639847457408905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.606901228427887},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5814704298973083},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5192663669586182},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4859062731266022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.478158563375473},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4468546509742737},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.4462347626686096},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.4263547360897064},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.4219716489315033},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.2915206551551819}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7516511678695679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155090570449829},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6930945515632629},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.673879861831665},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.639847457408905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.606901228427887},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5814704298973083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5192663669586182},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4859062731266022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.478158563375473},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4468546509742737},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.4462347626686096},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.4263547360897064},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4219716489315033},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2915206551551819},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4114/intartif.vol24iss68pp72-88","is_oa":true,"landing_page_url":"https://doi.org/10.4114/intartif.vol24iss68pp72-88","pdf_url":null,"source":{"id":"https://openalex.org/S4210203986","display_name":"INTELIGENCIA ARTIFICIAL","issn_l":"1137-3601","issn":["1137-3601","1988-3064"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321681","host_organization_name":"Asociaci\u00f3n Espa\u00f1ola para la Inteligencia Artificial","host_organization_lineage":["https://openalex.org/P4310321681"],"host_organization_lineage_names":["Asociaci\u00f3n Espa\u00f1ola para la Inteligencia Artificial"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Inteligencia Artificial","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8437f3a053d44ca8bd13389c3929b4b3","is_oa":true,"landing_page_url":"https://doaj.org/article/8437f3a053d44ca8bd13389c3929b4b3","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":"Inteligencia Artificial, Vol 24, Iss 68 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.4114/intartif.vol24iss68pp72-88","is_oa":true,"landing_page_url":"https://doi.org/10.4114/intartif.vol24iss68pp72-88","pdf_url":null,"source":{"id":"https://openalex.org/S4210203986","display_name":"INTELIGENCIA ARTIFICIAL","issn_l":"1137-3601","issn":["1137-3601","1988-3064"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321681","host_organization_name":"Asociaci\u00f3n Espa\u00f1ola para la Inteligencia Artificial","host_organization_lineage":["https://openalex.org/P4310321681"],"host_organization_lineage_names":["Asociaci\u00f3n Espa\u00f1ola para la Inteligencia Artificial"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Inteligencia Artificial","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2078744341","https://openalex.org/W2029555411","https://openalex.org/W2774439323","https://openalex.org/W2397092005","https://openalex.org/W3151530686","https://openalex.org/W1509265476","https://openalex.org/W2981446648","https://openalex.org/W2183678285","https://openalex.org/W4383568364","https://openalex.org/W2343937073"],"abstract_inverted_index":{"The":[0,82],"ongoing":[1],"development":[2],"of":[3,13,47,92,117,125,142,151],"computer":[4],"systems":[5],"requires":[6],"massive":[7],"software":[8,39,55,65],"projects.":[9],"Running":[10],"the":[11,45,106,123,126,133,138,148,152,175,187,196,202],"components":[12],"these":[14],"huge":[15],"projects":[16],"for":[17,38],"testing":[18],"purposes":[19],"might":[20],"be":[21,29],"a":[22,69,73,114,170,183],"costly":[23],"process;":[24],"therefore,":[25],"parameter":[26],"estimation":[27],"can":[28],"used":[30],"instead.":[31],"Software":[32],"defect":[33,56,66,108],"prediction":[34,57,67,84,109,128,155,190],"models":[35],"are":[36],"crucial":[37],"quality":[40],"assurance.":[41],"This":[42],"study":[43],"investigates":[44],"impact":[46],"dataset":[48,161,180],"size":[49,181],"and":[50,72],"feature":[51,97],"selection":[52,98],"algorithms":[53,99],"on":[54,89,111,186],"models.":[58],"We":[59,102,144],"use":[60],"two":[61],"approaches":[62],"to":[63,136],"build":[64],"models:":[68],"statistical":[70],"approach":[71,76],"machine":[74],"learning":[75],"with":[77,113,160],"support":[78],"vector":[79],"machines":[80],"(SVMs).":[81],"fault":[83,127,154,189],"model":[85,110,156],"was":[86],"built":[87],"based":[88],"four":[90,96],"datasets":[91,112,194],"different":[93],"sizes.":[94],"Additionally,":[95],"were":[100],"used.":[101],"found":[103,146,178],"that":[104,147,179],"applying":[105],"SVM":[107,153,188],"reduced":[115,193],"number":[116],"measures":[118],"as":[119],"features":[120],"may":[121],"enhance":[122],"accuracy":[124],"model.":[129,191],"Also,":[130],"it":[131],"directs":[132],"test":[134],"effort":[135],"maintain":[137],"most":[139],"influential":[140],"set":[141],"metrics.":[143],"also":[145],"running":[149],"time":[150],"is":[157],"not":[158,168],"consistent":[159],"size.":[162],"Therefore,":[163],"having":[164],"fewer":[165],"metrics":[166],"does":[167],"guarantee":[169],"shorter":[171],"execution":[172],"time.":[173],"From":[174],"experiments,":[176],"we":[177],"has":[182],"direct":[184],"influence":[185],"However,":[192],"performed":[195],"same":[197],"or":[198],"slightly":[199],"lower":[200],"than":[201],"original":[203],"datasets.":[204]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}