{"id":"https://openalex.org/W2218021565","doi":"https://doi.org/10.1109/tse.2016.2553030","title":"Comments on \u201cResearcher Bias: The Use of Machine Learning in Software Defect Prediction\u201d","display_name":"Comments on \u201cResearcher Bias: The Use of Machine Learning in Software Defect Prediction\u201d","publication_year":2016,"publication_date":"2016-04-11","ids":{"openalex":"https://openalex.org/W2218021565","doi":"https://doi.org/10.1109/tse.2016.2553030","mag":"2218021565"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2016.2553030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2016.2553030","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/A5081449581","display_name":"Chakkrit Tantithamthavorn","orcid":"https://orcid.org/0000-0002-5516-9984"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Chakkrit Tantithamthavorn","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043053174","display_name":"Shane McIntosh","orcid":"https://orcid.org/0000-0002-0193-3975"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shane McIntosh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"School of Computing, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011588138","display_name":"Kenichi Matsumoto","orcid":"https://orcid.org/0000-0002-7418-9323"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenichi Matsumoto","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081449581"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":20.5682,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.99246096,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"42","issue":"11","first_page":"1092","last_page":"1094"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":0.9972000122070312,"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":0.9821000099182129,"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/metric","display_name":"Metric (unit)","score":0.7255956530570984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724713146686554},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5586119890213013},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5454424619674683},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.5377443432807922},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5270545482635498},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.5066347718238831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4803539514541626},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47939515113830566},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4582407474517822},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.4529106914997101},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43547266721725464},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.4113944172859192},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.26357221603393555},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.2263716459274292},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14703962206840515},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08054354786872864}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7255956530570984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724713146686554},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5586119890213013},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5454424619674683},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.5377443432807922},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5270545482635498},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5066347718238831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4803539514541626},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47939515113830566},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4582407474517822},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.4529106914997101},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43547266721725464},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.4113944172859192},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.26357221603393555},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2263716459274292},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14703962206840515},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08054354786872864},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2016.2553030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2016.2553030","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1493790738","https://openalex.org/W1535807333","https://openalex.org/W1993555269","https://openalex.org/W1995945562","https://openalex.org/W2005504865","https://openalex.org/W2045855551","https://openalex.org/W2055566656","https://openalex.org/W2078793617","https://openalex.org/W2092388562","https://openalex.org/W2107031757","https://openalex.org/W2115709314","https://openalex.org/W2118283821","https://openalex.org/W2126650229","https://openalex.org/W2142635246","https://openalex.org/W2401615183","https://openalex.org/W2582743722","https://openalex.org/W2797062063","https://openalex.org/W3149745985","https://openalex.org/W4212867478","https://openalex.org/W4239863959","https://openalex.org/W4255783720","https://openalex.org/W4399568670","https://openalex.org/W4399637125","https://openalex.org/W4399639422","https://openalex.org/W6733261796","https://openalex.org/W6869529699","https://openalex.org/W6869544649"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W2494189957","https://openalex.org/W2079121834","https://openalex.org/W2119956050","https://openalex.org/W2116876706","https://openalex.org/W2181911813","https://openalex.org/W2350290471","https://openalex.org/W1792767331","https://openalex.org/W4383180931","https://openalex.org/W2519454625"],"abstract_inverted_index":{"Shepperd":[0,35],"et":[1,36],"al.":[2],"find":[3,99],"that":[4,41,59,100,118,152],"the":[5,18,24,54,67,79,82,92,101,109,119,122,126,138],"reported":[6],"performance":[7,127],"of":[8,20,34,81,94,128,140,159],"a":[9,14,46,64,105,129,156],"defect":[10,130],"prediction":[11,131],"model":[12,86,132],"shares":[13,45],"strong":[15,47,68,96],"relationship":[16,120],"with":[17,49,155],"group":[19,44,84,103,124],"researchers":[21,141,153],"who":[22],"construct":[23],"models.":[25],"In":[26],"this":[27,95],"paper,":[28],"we":[29,98],"perform":[30],"an":[31],"alternative":[32],"investigation":[33],"al.'s":[37],"data.":[38],"We":[39,150],"observe":[40],"(a)":[42],"research":[43,83,102,123],"association":[48,69],"other":[50],"explanatory":[51,72],"variables":[52,73],"(i.e.,":[53],"dataset":[55],"and":[56,88,125,148,161],"metric":[57,110],"families":[58],"are":[60,133],"used":[61],"to":[62,77,116,137,142,163],"build":[63],"model);":[65],"(b)":[66],"among":[70],"these":[71],"makes":[74],"it":[75],"difficult":[76],"discern":[78],"impact":[80,93,107],"on":[85],"performance;":[87],"(c)":[89],"after":[90],"mitigating":[91],"association,":[97],"has":[104],"smaller":[106],"than":[108],"family.":[111],"These":[112],"observations":[113],"lead":[114],"us":[115],"conclude":[117],"between":[121],"more":[134],"likely":[135],"due":[136],"tendency":[139],"reuse":[143],"experimental":[144],"components":[145],"(e.g.,":[146],"datasets":[147,160],"metrics).":[149],"recommend":[151],"experiment":[154],"broader":[157],"selection":[158],"metrics":[162],"combat":[164],"any":[165],"potential":[166],"bias":[167],"in":[168],"their":[169],"results.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}