{"id":"https://openalex.org/W1634225624","doi":"https://doi.org/10.1109/mipro.2015.7160316","title":"Data collection for Software Defect Prediction - An exploratory case study of open source software projects","display_name":"Data collection for Software Defect Prediction - An exploratory case study of open source software projects","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1634225624","doi":"https://doi.org/10.1109/mipro.2015.7160316","mag":"1634225624"},"language":"en","primary_location":{"id":"doi:10.1109/mipro.2015.7160316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mipro.2015.7160316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)","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/A5088320075","display_name":"Goran Mau\u0161a","orcid":"https://orcid.org/0000-0002-0643-4577"},"institutions":[{"id":"https://openalex.org/I154347574","display_name":"University of Rijeka","ror":"https://ror.org/05r8dqr10","country_code":"HR","type":"education","lineage":["https://openalex.org/I154347574"]}],"countries":["HR"],"is_corresponding":true,"raw_author_name":"Goran Mausa","raw_affiliation_strings":["Faculty of Engineering, University of Rijeka, Rijeka, Croatia","Faculty of Engineering, University of Rijeka, Croatia#TAB#"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, University of Rijeka, Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]},{"raw_affiliation_string":"Faculty of Engineering, University of Rijeka, Croatia#TAB#","institution_ids":["https://openalex.org/I154347574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032987107","display_name":"Tihana Galinac Grbac","orcid":"https://orcid.org/0000-0002-4351-4082"},"institutions":[{"id":"https://openalex.org/I154347574","display_name":"University of Rijeka","ror":"https://ror.org/05r8dqr10","country_code":"HR","type":"education","lineage":["https://openalex.org/I154347574"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Tihana Galinac Grbac","raw_affiliation_strings":["Faculty of Engineering, University of Rijeka, Rijeka, Croatia","Faculty of Engineering, University of Rijeka, Croatia#TAB#"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, University of Rijeka, Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]},{"raw_affiliation_string":"Faculty of Engineering, University of Rijeka, Croatia#TAB#","institution_ids":["https://openalex.org/I154347574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004799429","display_name":"Bojana Dalbelo Ba\u0161i\u0107","orcid":"https://orcid.org/0000-0002-6028-133X"},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I154347574","display_name":"University of Rijeka","ror":"https://ror.org/05r8dqr10","country_code":"HR","type":"education","lineage":["https://openalex.org/I154347574"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Bojana Dalbelo Basic","raw_affiliation_strings":["Faculty of Engineering, University of Rijeka, Rijeka, Croatia","Faculty of Electrical Engineering and Computing, University of Zagreb, (Croatia)"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, University of Rijeka, Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, University of Zagreb, (Croatia)","institution_ids":["https://openalex.org/I181343428"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088320075"],"corresponding_institution_ids":["https://openalex.org/I154347574"],"apc_list":null,"apc_paid":null,"fwci":2.3838,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90508355,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"463","last_page":"469"},"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":0.9991000294685364,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008332252502441},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.6968108415603638},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5686665773391724},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.5533068180084229},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5298435688018799},{"id":"https://openalex.org/keywords/exploratory-research","display_name":"Exploratory research","score":0.50434410572052},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46162158250808716},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3343737721443176},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08663016557693481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008332252502441},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.6968108415603638},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5686665773391724},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.5533068180084229},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5298435688018799},{"id":"https://openalex.org/C85973986","wikidata":"https://www.wikidata.org/wiki/Q1091731","display_name":"Exploratory research","level":2,"score":0.50434410572052},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46162158250808716},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3343737721443176},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08663016557693481},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mipro.2015.7160316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mipro.2015.7160316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.550000011920929,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1975040830","https://openalex.org/W1988019447","https://openalex.org/W2009177817","https://openalex.org/W2039081830","https://openalex.org/W2049624350","https://openalex.org/W2052797840","https://openalex.org/W2068430427","https://openalex.org/W2090625011","https://openalex.org/W2097883090","https://openalex.org/W2115105080","https://openalex.org/W2141102013","https://openalex.org/W2146338950","https://openalex.org/W2149783794","https://openalex.org/W2151666086","https://openalex.org/W2161482408","https://openalex.org/W2162739315","https://openalex.org/W2163851162","https://openalex.org/W3143096207"],"related_works":["https://openalex.org/W2186048469","https://openalex.org/W3029267192","https://openalex.org/W1967509846","https://openalex.org/W4308662946","https://openalex.org/W2941073738","https://openalex.org/W2480059162","https://openalex.org/W2189632163","https://openalex.org/W4221068634","https://openalex.org/W2979507544","https://openalex.org/W2621101275"],"abstract_inverted_index":{"Software":[0],"Defect":[1],"Prediction":[2],"(SDP)":[3],"empirical":[4],"studies":[5],"are":[6,23,50,126],"highly":[7],"biased":[8],"with":[9],"the":[10,24,39,60,73,82,101,108,136,167],"quality":[11],"of":[12,26,84,138,155,158],"data":[13,27,31,43,148,169],"and":[14,28,78,92,112,135],"widely":[15],"suffer":[16],"from":[17],"limited":[18],"generalizations.":[19],"The":[20,122],"main":[21],"reasons":[22],"lack":[25],"its":[29],"systematic":[30],"collection":[32,44,83,90,149,170],"procedures.":[33],"Our":[34,141],"research":[35,142],"aims":[36],"at":[37],"producing":[38],"first":[40,61],"systematically":[41],"defined":[42],"procedure":[45,91],"for":[46,117,152],"SDP":[47,85,156],"datasets":[48],"that":[49,65,103],"obtained":[51],"by":[52,107],"linking":[53],"separate":[54],"development":[55,154],"repositories.":[56],"This":[57],"paper":[58],"is":[59],"step":[62],"to":[63,165],"achieving":[64],"objective,":[66],"performing":[67],"an":[68],"exploratory":[69,97],"study.":[70,98],"We":[71,99],"review":[72,114],"existing":[74],"literature":[75],"on":[76],"approaches":[77],"tools":[79,116],"used":[80],"in":[81,95],"datasets,":[86],"derive":[87],"a":[88],"detailed":[89],"test":[93],"it":[94],"this":[96],"quantify":[100],"bias":[102],"may":[104],"be":[105],"caused":[106],"issues":[109,125],"we":[110,113],"identified":[111],"35":[115],"software":[118],"product":[119],"metrics":[120],"collection.":[121],"most":[123],"critical":[124],"many-to-many":[127],"relation":[128],"between":[129],"bug-file":[130,133],"links,":[131],"duplicated":[132],"links":[134],"issue":[137],"untraceable":[139],"bugs.":[140],"provides":[143],"more":[144],"detailed,":[145],"experience":[146],"based":[147],"procedure,":[150],"crucial":[151],"further":[153],"body":[157],"knowledge.":[159],"Furthermore,":[160],"our":[161],"findings":[162],"enabled":[163],"us":[164],"develop":[166],"automatic":[168],"tool.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
