{"id":"https://openalex.org/W3153385371","doi":"https://doi.org/10.1109/tse.2021.3073920","title":"The Impact of Data Merging on the Interpretation of Cross-Project Just-In-Time Defect Models","display_name":"The Impact of Data Merging on the Interpretation of Cross-Project Just-In-Time Defect Models","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3153385371","doi":"https://doi.org/10.1109/tse.2021.3073920","mag":"3153385371"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2021.3073920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3073920","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Software Engineering","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/A5079401267","display_name":"Dayi Lin","orcid":"https://orcid.org/0000-0002-4034-6650"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dayi Lin","raw_affiliation_strings":["Centre for Software Excellence, Huawei, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4034-6650","affiliations":[{"raw_affiliation_string":"Centre for Software Excellence, Huawei, ON, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081449581","display_name":"Chakkrit Tantithamthavorn","orcid":"https://orcid.org/0000-0002-5516-9984"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chakkrit Tantithamthavorn","raw_affiliation_strings":["Faculty of Information Technology, Monash University, Clayton, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5516-9984","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091586373","display_name":"Ahmed E. Hassan","orcid":"https://orcid.org/0000-0001-7749-5513"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed E. Hassan","raw_affiliation_strings":["School of Computing, Queen's University, Kingston, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4348,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94724626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"48","issue":"8","first_page":"2969","last_page":"2986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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/T11675","display_name":"Open Source Software Innovations","score":0.9696000218391418,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9681000113487244,"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/computer-science","display_name":"Computer science","score":0.7392854690551758},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.6510918736457825},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5591508746147156},{"id":"https://openalex.org/keywords/project-management","display_name":"Project management","score":0.4700827896595001},{"id":"https://openalex.org/keywords/mixed-model","display_name":"Mixed model","score":0.4208754897117615},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35306715965270996},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3431873917579651},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33686602115631104},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1773068606853485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1686498522758484},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13790777325630188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10696414113044739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392854690551758},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.6510918736457825},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5591508746147156},{"id":"https://openalex.org/C15952604","wikidata":"https://www.wikidata.org/wiki/Q179012","display_name":"Project management","level":2,"score":0.4700827896595001},{"id":"https://openalex.org/C16012445","wikidata":"https://www.wikidata.org/wiki/Q1501135","display_name":"Mixed model","level":2,"score":0.4208754897117615},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35306715965270996},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3431873917579651},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33686602115631104},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1773068606853485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1686498522758484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13790777325630188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10696414113044739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2021.3073920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3073920","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4416570303","display_name":"Practical and Explainable Analytics to Prevent Future Software Defects","funder_award_id":"DE200100941","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1909497710","https://openalex.org/W1980276147","https://openalex.org/W1989354793","https://openalex.org/W1994248747","https://openalex.org/W2006353560","https://openalex.org/W2007705030","https://openalex.org/W2019655958","https://openalex.org/W2046830558","https://openalex.org/W2057826716","https://openalex.org/W2059072625","https://openalex.org/W2060444352","https://openalex.org/W2061019658","https://openalex.org/W2066687630","https://openalex.org/W2076983043","https://openalex.org/W2082183626","https://openalex.org/W2089863833","https://openalex.org/W2101227285","https://openalex.org/W2104789242","https://openalex.org/W2108769867","https://openalex.org/W2110229593","https://openalex.org/W2120703352","https://openalex.org/W2132887549","https://openalex.org/W2147386665","https://openalex.org/W2150874999","https://openalex.org/W2155988679","https://openalex.org/W2157353183","https://openalex.org/W2158744032","https://openalex.org/W2276400542","https://openalex.org/W2328892620","https://openalex.org/W2367798545","https://openalex.org/W2380271241","https://openalex.org/W2474835145","https://openalex.org/W2543851504","https://openalex.org/W2594563067","https://openalex.org/W2606150376","https://openalex.org/W2735995639","https://openalex.org/W2755160617","https://openalex.org/W2766521509","https://openalex.org/W2767894374","https://openalex.org/W2792987835","https://openalex.org/W2795469443","https://openalex.org/W2909172538","https://openalex.org/W2954276596","https://openalex.org/W2963097549","https://openalex.org/W2963520355","https://openalex.org/W2963548617","https://openalex.org/W2999093514","https://openalex.org/W3013745307","https://openalex.org/W3046757114","https://openalex.org/W3086723730","https://openalex.org/W3134708177","https://openalex.org/W3141989311","https://openalex.org/W3163556840","https://openalex.org/W3174750614","https://openalex.org/W3175995826","https://openalex.org/W4205601502","https://openalex.org/W4236586490","https://openalex.org/W4296394699","https://openalex.org/W4299625508"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W4313320911","https://openalex.org/W4327743144","https://openalex.org/W4245077728","https://openalex.org/W2607424049","https://openalex.org/W4390922876","https://openalex.org/W3183204001","https://openalex.org/W4206302830","https://openalex.org/W2185941092","https://openalex.org/W4386782890"],"abstract_inverted_index":{"Just-In-Time":[0],"(JIT)":[1],"defect":[2,90],"models":[3,6,20,31,43,91,132],"are":[4,13,65,93,134,201],"classification":[5],"that":[7,12,56,68,92,126,133,154,183,225,237],"identify":[8],"the":[9,26,57,70,86,128,144,176,188,197,212],"code":[10],"commits":[11,61],"likely":[14,75],"to":[15,24,67,84,215,231],"introduce":[16],"defects.":[17],"Cross-project":[18],"JIT":[19,30,42,89,131,152,173,181,221],"have":[21],"been":[22],"introduced":[23],"address":[25],"suboptimal":[27],"performance":[28],"of":[29,47,59,62,69,88,102,110,117,120,130,160,199,219],"when":[32,196],"historical":[33],"data":[34,49,54,98,105,162],"is":[35,74,155,214],"limited.":[36],"However,":[37],"many":[38],"studies":[39],"built":[40,94,135],"cross-project":[41,220],"using":[44],"a":[45,63,100,114,151,158,171,179,233],"pool":[46,101,159],"mixed":[48,103,161],"from":[50,95,136,157,163],"multiple":[51,164],"projects":[52,138,165,200,240],"(i.e.,":[53,170],"merging)\u2014assuming":[55],"properties":[58],"defect-introducing":[60],"project":[64,97,104],"similar":[66],"other":[71,177],"projects,":[72,123],"which":[73],"not":[76],"true.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81,124,223],"set":[82],"out":[83],"investigate":[85],"interpretation":[87,129,218],"individual":[96,137,239],"and":[99,107,142,227,241],"with":[106],"without":[108,166,192],"consideration":[109],"project-level":[111,145,168,185],"variances.":[112],"Through":[113],"case":[115],"study":[116],"20":[118],"datasets":[119],"open":[121],"source":[122],"found":[125],"(1)":[127],"varies":[139],"among":[140],"projects;":[141],"(2)":[143],"variances":[146,169,186],"cannot":[147],"be":[148],"captured":[149],"by":[150],"model":[153,182],"trained":[156],"considering":[167],"global":[172],"model).":[174],"On":[175],"hand,":[178],"mixed-effect":[180,208,234],"considers":[184,238],"represents":[187],"different":[189,207],"interpretations":[190],"better,":[191],"sacrificing":[193],"performance,":[194],"especially":[195],"contexts":[198],"considered.":[202],"The":[203],"results":[204],"hold":[205],"for":[206],"learning":[209],"algorithms.":[210],"When":[211],"goal":[213],"derive":[216],"sound":[217],"models,":[222],"suggest":[224],"practitioners":[226],"researchers":[228],"should":[229],"opt":[230],"use":[232],"modelling":[235],"approach":[236],"contexts.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}