{"id":"https://openalex.org/W2523229043","doi":"https://doi.org/10.1145/2961111.2962620","title":"So You Need More Method Level Datasets for Your Software Defect Prediction?","display_name":"So You Need More Method Level Datasets for Your Software Defect Prediction?","publication_year":2016,"publication_date":"2016-09-08","ids":{"openalex":"https://openalex.org/W2523229043","doi":"https://doi.org/10.1145/2961111.2962620","mag":"2523229043"},"language":"en","primary_location":{"id":"doi:10.1145/2961111.2962620","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2961111.2962620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","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/A5025914196","display_name":"Thomas Shippey","orcid":"https://orcid.org/0000-0003-1890-3390"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Thomas Shippey","raw_affiliation_strings":["Computer Science, Brunel University London, Uxbridge, United Kingdon"],"affiliations":[{"raw_affiliation_string":"Computer Science, Brunel University London, Uxbridge, United Kingdon","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019248666","display_name":"Tracy Hall","orcid":"https://orcid.org/0000-0002-2728-9014"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tracy Hall","raw_affiliation_strings":["Computer Science, Brunel University London, Uxbridge, United Kingdon"],"affiliations":[{"raw_affiliation_string":"Computer Science, Brunel University London, Uxbridge, United Kingdon","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083706258","display_name":"Steve Counsell","orcid":"https://orcid.org/0000-0002-2939-8919"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Counsell","raw_affiliation_strings":["Computer Science, Brunel University London, Uxbridge, United Kingdon"],"affiliations":[{"raw_affiliation_string":"Computer Science, Brunel University London, Uxbridge, United Kingdon","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058470128","display_name":"David Bowes","orcid":"https://orcid.org/0000-0001-7014-2811"},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Bowes","raw_affiliation_strings":["Science and Technology Research Institute, University of Hertfordshire, Hatfield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Science and Technology Research Institute, University of Hertfordshire, Hatfield, United Kingdom","institution_ids":["https://openalex.org/I141584323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025914196"],"corresponding_institution_ids":["https://openalex.org/I59433898"],"apc_list":null,"apc_paid":null,"fwci":6.6349,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96676246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9988999962806702,"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":0.9952999949455261,"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":0.7304902672767639},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.586365818977356},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5099819898605347},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4206881523132324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3354133665561676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32272666692733765},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11736482381820679}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304902672767639},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.586365818977356},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5099819898605347},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4206881523132324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3354133665561676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32272666692733765},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11736482381820679}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2961111.2962620","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2961111.2962620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3659755872","display_name":null,"funder_award_id":"EP/M024083/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5097934752","display_name":null,"funder_award_id":"EP/L011751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8729536445","display_name":"USING FAULT CHARACTERISTICS TO IMPROVE SOFTWARE FAULT PREDICTION","funder_award_id":"EP/L011751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W168970045","https://openalex.org/W1611601820","https://openalex.org/W1969082431","https://openalex.org/W1987855178","https://openalex.org/W1988019447","https://openalex.org/W1989479444","https://openalex.org/W2023399666","https://openalex.org/W2027062921","https://openalex.org/W2031227255","https://openalex.org/W2068430427","https://openalex.org/W2095632607","https://openalex.org/W2097883090","https://openalex.org/W2100034782","https://openalex.org/W2100945416","https://openalex.org/W2110385988","https://openalex.org/W2114124859","https://openalex.org/W2126166995","https://openalex.org/W2126626812","https://openalex.org/W2142481192","https://openalex.org/W2149783794","https://openalex.org/W2151553346","https://openalex.org/W2151666086","https://openalex.org/W2157353183","https://openalex.org/W2171733741","https://openalex.org/W2172232422","https://openalex.org/W2179590804","https://openalex.org/W2249980257","https://openalex.org/W2367798545","https://openalex.org/W2394841101","https://openalex.org/W2395429379","https://openalex.org/W2547620887","https://openalex.org/W4235295935","https://openalex.org/W4298375254"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Context:":[0],"Defect":[1],"prediction":[2,32,56,88],"research":[3],"is":[4,26,33,43],"based":[5,93],"on":[6,94],"a":[7,90],"small":[8],"number":[9],"of":[10,24,169],"defect":[11,29,55,87,101,175],"datasets":[12,30,42,127,136,164],"and":[13,36,57,99,114,125,140],"most":[14],"are":[15],"at":[16],"class":[17],"not":[18,34],"method":[19],"level.":[20],"Consequently":[21],"our":[22,141],"knowledge":[23],"defects":[25],"limited.":[27],"Identifying":[28],"for":[31,54,86,128],"easy":[35],"extracting":[37],"quality":[38,60],"data":[39,62,142,152],"from":[40,63],"identified":[41,131],"even":[44],"more":[45],"difficult.":[46],"Goal:":[47],"Identify":[48],"open":[49,74],"source":[50,75],"Java":[51],"systems":[52,170],"suitable":[53,85],"extract":[58,111],"high":[59],"fault":[61,112,124],"these":[64,135],"datasets.":[65],"Method:":[66],"We":[67,77,104,120,133],"used":[68,173],"the":[69,95,129,167],"Boa":[70],"to":[71,83,110,147,158],"identify":[72],"candidate":[73],"systems.":[76,132],"reduce":[78],"50,000":[79],"potential":[80],"candidates":[81],"down":[82],"23":[84,130],"using":[89,117],"selection":[91],"criteria":[92],"system's":[96],"software":[97],"repository":[98],"its":[100],"tracking":[102],"system.":[103],"use":[105],"an":[106],"enhanced":[107],"SZZ":[108],"algorithm":[109],"information":[113],"calculate":[115],"metrics":[116,126],"JHawk.":[118],"Result:":[119],"have":[121],"produced":[122],"138":[123],"make":[134],"(the":[137],"ELFF":[138],"datasets)":[139],"extraction":[143],"tools":[144],"freely":[145],"available":[146],"future":[148,156],"researchers.":[149],"Conclusions:":[150],"The":[151],"we":[153],"provide":[154],"enables":[155],"studies":[157],"proceed":[159],"with":[160],"minimal":[161],"effort.":[162],"Our":[163],"significantly":[165],"increase":[166],"pool":[168],"currently":[171],"being":[172],"in":[174],"analysis":[176],"studies.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}