{"id":"https://openalex.org/W4320074595","doi":"https://doi.org/10.1145/3543895.3543924","title":"Stratifying large software files to improve prediction performance in software defect prediction","display_name":"Stratifying large software files to improve prediction performance in software defect prediction","publication_year":2022,"publication_date":"2022-05-25","ids":{"openalex":"https://openalex.org/W4320074595","doi":"https://doi.org/10.1145/3543895.3543924"},"language":"en","primary_location":{"id":"doi:10.1145/3543895.3543924","doi":"https://doi.org/10.1145/3543895.3543924","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543895.3543924","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543895.3543924","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Applied Computing & Information Technology","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543895.3543924","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069779936","display_name":"Yasser Ali Alshehri","orcid":"https://orcid.org/0000-0003-1134-4514","observed_orcids":["https://orcid.org/0000-0003-1134-4514"]},"institutions":[{"id":"https://openalex.org/I4400600957","display_name":"Yanbu Industrial College","ror":"https://ror.org/01sxpmm41","country_code":"SA","type":"education","lineage":["https://openalex.org/I4400600957"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Yasser Ali Alshehri","raw_affiliation_strings":["Computer Science and Engineering Dept, Yanbu Industrial College, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-1134-4514","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Dept, Yanbu Industrial College, Saudi Arabia","institution_ids":["https://openalex.org/I4400600957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014122381","display_name":"Noha Alnazzawi","orcid":"https://orcid.org/0000-0003-3265-0297","observed_orcids":["https://orcid.org/0000-0003-3265-0297"]},"institutions":[{"id":"https://openalex.org/I4400600957","display_name":"Yanbu Industrial College","ror":"https://ror.org/01sxpmm41","country_code":"SA","type":"education","lineage":["https://openalex.org/I4400600957"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Noha Alnazzawi","raw_affiliation_strings":["Computer Science and Engineering Dept, Yanbu Industrial College, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-3265-0297","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Dept, Yanbu Industrial College, Saudi Arabia","institution_ids":["https://openalex.org/I4400600957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026701209","display_name":"Haneen Hijazi","orcid":"https://orcid.org/0000-0001-7364-0218","observed_orcids":["https://orcid.org/0000-0001-7364-0218"]},"institutions":[{"id":"https://openalex.org/I157392197","display_name":"Hashemite University","ror":"https://ror.org/04a1r5z94","country_code":"JO","type":"education","lineage":["https://openalex.org/I157392197"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Haneen Hijazi","raw_affiliation_strings":["Dept of Software Engrg, Hashemite University, Jordan"],"raw_orcid":"https://orcid.org/0000-0001-7364-0218","affiliations":[{"raw_affiliation_string":"Dept of Software Engrg, Hashemite University, Jordan","institution_ids":["https://openalex.org/I157392197"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102710351","display_name":"Rawan Alharbi","orcid":"https://orcid.org/0000-0002-3044-1208","observed_orcids":["https://orcid.org/0000-0002-3044-1208"]},"institutions":[{"id":"https://openalex.org/I72264486","display_name":"University of Tabuk","ror":"https://ror.org/04yej8x59","country_code":"SA","type":"education","lineage":["https://openalex.org/I72264486"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Rawan Alharbi","raw_affiliation_strings":["Computer Science and Engineering Dept, Tabuk University, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-3044-1208","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Dept, Tabuk University, Saudi Arabia","institution_ids":["https://openalex.org/I72264486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1753,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4330702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":9.999999747378752e-05,"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/software-defect-prediction","display_name":"software defect prediction","score":0.996999979019165},{"id":"https://openalex.org/keywords/software-size","display_name":"program size","score":0.6729999780654907},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"stratified sampling","score":0.8930000066757202},{"id":"https://openalex.org/keywords/j48","display_name":"J48 decision tree","score":0.8370000123977661},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.9950000047683716},{"id":"https://openalex.org/keywords/predictive-performance","display_name":"predictive performance","score":0.4959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386679649353027},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.6803843975067139},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5554714798927307},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.36284154653549194},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31965601444244385},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09236901998519897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543895.3543924","doi":"https://doi.org/10.1145/3543895.3543924","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543895.3543924","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543895.3543924","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Applied Computing & Information Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543895.3543924","doi":"https://doi.org/10.1145/3543895.3543924","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543895.3543924","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543895.3543924","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Applied Computing & Information Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4320074595.pdf","grobid_xml":"https://content.openalex.org/works/W4320074595.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1534563209","https://openalex.org/W1968652658","https://openalex.org/W2026750231","https://openalex.org/W2031812206","https://openalex.org/W2057179820","https://openalex.org/W2065547122","https://openalex.org/W2070983362","https://openalex.org/W2081025867","https://openalex.org/W2081917329","https://openalex.org/W2082795423","https://openalex.org/W2105776892","https://openalex.org/W2122475259","https://openalex.org/W2127623179","https://openalex.org/W2132887549","https://openalex.org/W2139784826","https://openalex.org/W2142481192","https://openalex.org/W2143075743","https://openalex.org/W2151666086","https://openalex.org/W2160928200","https://openalex.org/W2296517388","https://openalex.org/W2304692780","https://openalex.org/W2474743723","https://openalex.org/W2802988819","https://openalex.org/W2811103478","https://openalex.org/W2962562836","https://openalex.org/W3031774730","https://openalex.org/W3092994387","https://openalex.org/W3141989311","https://openalex.org/W4241197470","https://openalex.org/W4398153366"],"related_works":["https://openalex.org/W4386460433","https://openalex.org/W2159610968","https://openalex.org/W2895264974","https://openalex.org/W3172407116","https://openalex.org/W2091062598","https://openalex.org/W109123456","https://openalex.org/W2324666559","https://openalex.org/W1986683951","https://openalex.org/W1985797722","https://openalex.org/W3209618143"],"abstract_inverted_index":{"Size":[0],"is":[1,121],"one":[2],"of":[3,42,79,110,137],"the":[4,40,69,77,107,131],"significant":[5],"factors":[6],"associated":[7],"with":[8,118],"bugs,":[9],"and":[10,53,74,83,94,141],"it":[11],"has":[12],"been":[13],"used":[14,87],"to":[15,97],"predict":[16],"software":[17,23,55],"faults.":[18],"We":[19,67,86],"believe":[20],"that":[21,115],"stratifying":[22,45],"files":[24,120],"based":[25,48,61],"on":[26,49,62,106],"size":[27,43,52],"can":[28],"play":[29],"an":[30,63],"essential":[31],"role":[32],"in":[33,57,126,144],"improving":[34],"prediction":[35],"performance.":[36],"This":[37],"study":[38],"explored":[39],"effect":[41],"by":[44],"our":[46],"sample":[47],"each":[50,80,145],"unit\u2019s":[51],"distributing":[54],"units":[56],"multiple":[58],"stratified":[59,68,81],"groups":[60],"equal":[64],"distribution":[65],"approach.":[66],"Eclipse":[70],"Europa":[71],"project":[72],"files,":[73],"we":[75],"reported":[76],"performance":[78,139],"group":[82,109],"compared":[84],"them.":[85],"two":[88],"popular":[89],"classifiers,":[90],"decision":[91],"tree":[92],"J48,":[93],"random":[95],"forest,":[96],"implement":[98],"this":[99],"experiment.":[100],"These":[101],"classifiers":[102],"presented":[103],"similar":[104],"results":[105,113,132],"same":[108],"files.":[111,128],"The":[112],"indicated":[114],"predicting":[116,124],"faults":[117],"large":[119],"better":[122],"than":[123],"those":[125],"small":[127],"In":[129],"addition,":[130],"showed":[133],"higher":[134],"median":[135],"values":[136],"all":[138],"measures":[140],"less":[142],"variation":[143],"measure.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2023-02-12T00:00:00"}