{"id":"https://openalex.org/W2545762469","doi":"https://doi.org/10.1002/smr.1821","title":"Detecting duplicate bug reports with software engineering domain knowledge","display_name":"Detecting duplicate bug reports with software engineering domain knowledge","publication_year":2016,"publication_date":"2016-10-27","ids":{"openalex":"https://openalex.org/W2545762469","doi":"https://doi.org/10.1002/smr.1821","mag":"2545762469"},"language":"en","primary_location":{"id":"doi:10.1002/smr.1821","is_oa":false,"landing_page_url":"https://doi.org/10.1002/smr.1821","pdf_url":null,"source":{"id":"https://openalex.org/S4210172359","display_name":"Journal of Software Evolution and Process","issn_l":"2047-7473","issn":["2047-7473","2047-7481"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software: Evolution and Process","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/A5052681145","display_name":"Karan Aggarwal","orcid":"https://orcid.org/0000-0002-9038-0099"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Karan Aggarwal","raw_affiliation_strings":["Department of Computing Science University of Alberta  Edmonton Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta  Edmonton Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082031365","display_name":"Finbarr Timbers","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Finbarr Timbers","raw_affiliation_strings":["Department of Computing Science University of Alberta  Edmonton Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta  Edmonton Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001645085","display_name":"Tanner Rutgers","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tanner Rutgers","raw_affiliation_strings":["Department of Computing Science University of Alberta  Edmonton Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta  Edmonton Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070785370","display_name":"Abram Hindle","orcid":"https://orcid.org/0000-0002-4373-4958"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Abram Hindle","raw_affiliation_strings":["Department of Computing Science University of Alberta  Edmonton Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta  Edmonton Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048978461","display_name":"Eleni Stroulia","orcid":"https://orcid.org/0000-0002-8784-8236"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eleni Stroulia","raw_affiliation_strings":["Department of Computing Science University of Alberta  Edmonton Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta  Edmonton Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027200864","display_name":"Russell Greiner","orcid":"https://orcid.org/0000-0001-8327-934X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Russell Greiner","raw_affiliation_strings":["Department of Computing Science University of Alberta  Edmonton Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta  Edmonton Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070785370"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":12.1793,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98465294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":"3","first_page":null,"last_page":null},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.987500011920929,"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":0.9842000007629395,"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":0.7668852806091309},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5246831774711609},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5164111256599426},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5007903575897217},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45375630259513855},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4486159384250641},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44657909870147705},{"id":"https://openalex.org/keywords/domain-engineering","display_name":"Domain engineering","score":0.44100499153137207},{"id":"https://openalex.org/keywords/software-mining","display_name":"Software mining","score":0.41948258876800537},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3929426968097687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3875121772289276},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.373241126537323},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.2951872646808624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668852806091309},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5246831774711609},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5164111256599426},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5007903575897217},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45375630259513855},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4486159384250641},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44657909870147705},{"id":"https://openalex.org/C5977032","wikidata":"https://www.wikidata.org/wiki/Q5289815","display_name":"Domain engineering","level":5,"score":0.44100499153137207},{"id":"https://openalex.org/C103520596","wikidata":"https://www.wikidata.org/wiki/Q7554328","display_name":"Software mining","level":5,"score":0.41948258876800537},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3929426968097687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3875121772289276},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.373241126537323},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.2951872646808624},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/smr.1821","is_oa":false,"landing_page_url":"https://doi.org/10.1002/smr.1821","pdf_url":null,"source":{"id":"https://openalex.org/S4210172359","display_name":"Journal of Software Evolution and Process","issn_l":"2047-7473","issn":["2047-7473","2047-7481"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software: Evolution and Process","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W73830396","https://openalex.org/W1576624296","https://openalex.org/W1605034451","https://openalex.org/W1972275887","https://openalex.org/W1981109290","https://openalex.org/W1999910737","https://openalex.org/W2018582844","https://openalex.org/W2070366414","https://openalex.org/W2072069252","https://openalex.org/W2107316307","https://openalex.org/W2125587588","https://openalex.org/W2130146200","https://openalex.org/W2133108681","https://openalex.org/W2136695057","https://openalex.org/W2139270835","https://openalex.org/W2158133897","https://openalex.org/W2165022036","https://openalex.org/W2167630669","https://openalex.org/W2238653922","https://openalex.org/W2604000799","https://openalex.org/W3138780885","https://openalex.org/W3149901392"],"related_works":["https://openalex.org/W4246180183","https://openalex.org/W2170664339","https://openalex.org/W2102997561","https://openalex.org/W1587887330","https://openalex.org/W2023019272","https://openalex.org/W4285194545","https://openalex.org/W2374471852","https://openalex.org/W3147473711","https://openalex.org/W147630542","https://openalex.org/W1489170632"],"abstract_inverted_index":{"Bug":[0],"deduplication,":[1],"ie,":[2],"recognizing":[3],"bug":[4,84],"reports":[5,85],"that":[6,37,133],"refer":[7],"to":[8,45,49,80,87,106,155,166,193],"the":[9,17,35,42,51,67,109,157,161,173],"same":[10],"problem,":[11],"is":[12],"a":[13,75,92,104,119,153],"challenging":[14],"task":[15],"in":[16,115,122,160],"software\u2010engineering":[18,59,72,158],"life":[19],"cycle.":[20],"Researchers":[21],"have":[22,91],"proposed":[23,66],"several":[24],"methods":[25],"primarily":[26],"relying":[27],"on":[28],"information\u2010retrieval":[29],"techniques.":[30],"Our":[31,98],"work":[32,130],"motivated":[33],"by":[34,56,131,189],"intuition":[36],"domain":[38],"knowledge":[39,159],"can":[40,136],"provide":[41],"relevant":[43],"context":[44,183],"enhance":[46],"effectiveness,":[47],"attempts":[48],"improve":[50],"use":[52],"of":[53,77,95,111,163,175],"information":[54,79],"retrieval":[55],"augmenting":[57],"with":[58,118],"knowledge.":[60],"In":[61,124],"our":[62,129],"previous":[63],"work,":[64],"we":[65,127],"software\u2010literature\u2010context":[68],"method":[69],"for":[70],"using":[71],"literature":[73],"as":[74],"source":[76],"contextual":[78,164,177],"detect":[81],"duplicates.":[82,97],"If":[83],"relate":[86],"similar":[88],"subjects,":[89],"they":[90],"better":[93],"chance":[94],"being":[96,100],"method,":[99],"largely":[101],"automated,":[102],"has":[103],"potential":[105],"substantially":[107],"decrease":[108],"level":[110],"manual":[112],"effort":[113],"involved":[114],"conventional":[116],"techniques":[117],"minor":[120],"trade\u2010off":[121],"accuracy.":[123],"this":[125],"study,":[126],"extend":[128],"demonstrating":[132],"domain\u2010specific":[134,176],"features":[135,143,178],"be":[137],"applied":[138],"across":[139],"projects":[140],"than":[141],"project\u2010specific":[142],"demonstrated":[144],"previously":[145],"while":[146],"still":[147],"maintaining":[148],"performance.":[149],"We":[150,170],"also":[151,171],"introduce":[152],"hierarchy\u2010of\u2010context":[154],"capture":[156],"realms":[162],"space":[165],"produce":[167],"performance":[168],"gains.":[169],"highlight":[172],"importance":[174],"through":[179],"cross\u2010domain":[180],"contexts:":[181],"adding":[182],"improved":[184,188],"accuracy;":[185],"Kappa":[186],"scores":[187],"at":[190],"least":[191],"3.8%":[192],"10.8%":[194],"per":[195],"project.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
