{"id":"https://openalex.org/W1973540172","doi":"https://doi.org/10.1145/1137983.1138012","title":"Predicting defect densities in source code files with decision tree learners","display_name":"Predicting defect densities in source code files with decision tree learners","publication_year":2006,"publication_date":"2006-05-22","ids":{"openalex":"https://openalex.org/W1973540172","doi":"https://doi.org/10.1145/1137983.1138012","mag":"1973540172"},"language":"en","primary_location":{"id":"doi:10.1145/1137983.1138012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1137983.1138012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 international workshop on Mining software repositories","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038599296","display_name":"Patrick Knab","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Patrick Knab","raw_affiliation_strings":["University of Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052107936","display_name":"Martin Pinzger","orcid":"https://orcid.org/0000-0002-5536-3859"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Martin Pinzger","raw_affiliation_strings":["University of Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073592405","display_name":"Abraham Bernstein","orcid":"https://orcid.org/0000-0002-0128-4602"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Abraham Bernstein","raw_affiliation_strings":["University of Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"125"},"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":0.9983000159263611,"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":0.9915000200271606,"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":0.835758626461029},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6657047867774963},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6310533285140991},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.6042791604995728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5954562425613403},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5307386517524719},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5221219658851624},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4749740958213806},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4715043604373932},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4668140411376953},{"id":"https://openalex.org/keywords/decision-tree-learning","display_name":"Decision tree learning","score":0.4363487660884857},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43513649702072144},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.433931827545166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.414113312959671},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.26377344131469727},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18992438912391663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835758626461029},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6657047867774963},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6310533285140991},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.6042791604995728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5954562425613403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5307386517524719},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5221219658851624},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4749740958213806},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4715043604373932},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4668140411376953},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.4363487660884857},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43513649702072144},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.433931827545166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414113312959671},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.26377344131469727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18992438912391663},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1137983.1138012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1137983.1138012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 international workshop on Mining software repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.452.8933","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.452.8933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://flosshub.org/system/files/119Predicting.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1597810835","https://openalex.org/W2100945416","https://openalex.org/W2110385988","https://openalex.org/W2113658292","https://openalex.org/W2121528215","https://openalex.org/W2121866145","https://openalex.org/W2123127356","https://openalex.org/W2137855426","https://openalex.org/W2141051748","https://openalex.org/W2141558501","https://openalex.org/W2147105902","https://openalex.org/W2150786161","https://openalex.org/W2158864412","https://openalex.org/W2159610968","https://openalex.org/W2966207845","https://openalex.org/W6678836955"],"related_works":["https://openalex.org/W2113128227","https://openalex.org/W632256878","https://openalex.org/W4211197663","https://openalex.org/W2491403535","https://openalex.org/W3123068371","https://openalex.org/W119580281","https://openalex.org/W2479811461","https://openalex.org/W2104915799","https://openalex.org/W2355429491","https://openalex.org/W2043894790"],"abstract_inverted_index":{"With":[0],"the":[1,8,28,34,77,102,110,116,138],"advent":[2],"of":[3,31,37,118,132,140,160,186],"open":[4,79],"source":[5,15,80,89,121],"software":[6,169],"repositories":[7],"data":[9,32,48,74,86],"available":[10],"for":[11,115,126,133],"defect":[12,38,59,93],"prediction":[13,39,61],"in":[14,168],"files":[16],"increased":[17],"tremendously.":[18],"Although":[19],"traditional":[20],"statistics":[21],"turned":[22],"out":[23],"to":[24,162],"derive":[25],"reasonable":[26],"results":[27,182],"sheer":[29],"amount":[30],"and":[33,50,62,92],"problem":[35],"context":[36],"demand":[40],"sophisticated":[41],"analysis":[42],"such":[43],"as":[44],"provided":[45],"by":[46,149],"current":[47],"mining":[49],"machine":[51],"learning":[52],"techniques.In":[53],"this":[54],"work":[55],"we":[56,105,155],"focus":[57],"on":[58,72],"density":[60],"present":[63],"an":[64],"approach":[65],"that":[66,174],"applies":[67],"a":[68,113,158,175],"decision":[69,128],"tree":[70,129,177],"learner":[71,178],"evolution":[73,85],"extracted":[75],"from":[76,96],"Mozilla":[78,99],"web":[81],"browser":[82],"project.":[83],"The":[84,123],"includes":[87],"different":[88],"code,":[90],"modification,":[91],"measures":[94,104],"computed":[95],"seven":[97],"recent":[98],"releases.":[100],"Among":[101],"modification":[103],"also":[106],"take":[107],"into":[108],"account":[109],"change":[111],"coupling,":[112],"measure":[114],"number":[117,159],"change-dependencies":[119],"between":[120],"files.":[122],"main":[124],"reason":[125],"choosing":[127],"learners,":[130],"instead":[131],"example":[134],"neural":[135],"nets,":[136],"was":[137],"goal":[139],"finding":[141],"underlying":[142],"rules":[143],"which":[144],"can":[145,179],"be":[146],"easily":[147],"interpreted":[148],"humans.":[150],"To":[151],"find":[152],"these":[153],"rules,":[154],"set":[156],"up":[157],"experiments":[161,172],"test":[163],"common":[164],"hypotheses":[165],"regarding":[166],"defects":[167],"entities.":[170],"Our":[171],"showed,":[173],"simple":[176],"produce":[180],"good":[181],"with":[183],"various":[184],"sets":[185],"input":[187],"data.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
