{"id":"https://openalex.org/W1994857824","doi":"https://doi.org/10.1145/2396761.2396869","title":"Learning to rank duplicate bug reports","display_name":"Learning to rank duplicate bug reports","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W1994857824","doi":"https://doi.org/10.1145/2396761.2396869","mag":"1994857824"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2396869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2396869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","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/A5059763207","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0002-0896-5662"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059763207"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.586,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.96265267,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"852","last_page":"861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9922999739646912,"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/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.8104103803634644},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.5864615440368652},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5656073689460754},{"id":"https://openalex.org/keywords/software-regression","display_name":"Software regression","score":0.5588701963424683},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5369531512260437},{"id":"https://openalex.org/keywords/eclipse","display_name":"Eclipse","score":0.5053306221961975},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.47152718901634216},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4531722962856293},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4398314654827118},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43318891525268555},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4310985803604126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39587610960006714},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.17342939972877502},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.1411745250225067},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.125393807888031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104103803634644},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.5864615440368652},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5656073689460754},{"id":"https://openalex.org/C191727507","wikidata":"https://www.wikidata.org/wiki/Q24346","display_name":"Software regression","level":5,"score":0.5588701963424683},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5369531512260437},{"id":"https://openalex.org/C2778505590","wikidata":"https://www.wikidata.org/wiki/Q141022","display_name":"Eclipse","level":2,"score":0.5053306221961975},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.47152718901634216},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4531722962856293},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4398314654827118},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43318891525268555},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4310985803604126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39587610960006714},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.17342939972877502},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.1411745250225067},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.125393807888031},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2396761.2396869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2396869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:vitalprd00.priv:uon:31905","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.13/1357327","pdf_url":null,"source":{"id":"https://openalex.org/S4377196612","display_name":"NOVA (University of Newcastle Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2007842132","https://openalex.org/W2012833704","https://openalex.org/W2047221353","https://openalex.org/W2067802667","https://openalex.org/W2079317829","https://openalex.org/W2085030399","https://openalex.org/W2085922539","https://openalex.org/W2086511124","https://openalex.org/W2091158010","https://openalex.org/W2108862644","https://openalex.org/W2109803107","https://openalex.org/W2120058970","https://openalex.org/W2125398996","https://openalex.org/W2125587588","https://openalex.org/W2130146200","https://openalex.org/W2138790992","https://openalex.org/W2139270835","https://openalex.org/W2142537246","https://openalex.org/W2143331230","https://openalex.org/W2149427297","https://openalex.org/W2155229791","https://openalex.org/W2156833313","https://openalex.org/W2164634022","https://openalex.org/W2165022036","https://openalex.org/W2167630669","https://openalex.org/W2988119488","https://openalex.org/W4285719527","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W3009111612","https://openalex.org/W2044225531","https://openalex.org/W2442359302","https://openalex.org/W2597543511","https://openalex.org/W3045036521","https://openalex.org/W2135303064","https://openalex.org/W2901462014","https://openalex.org/W3004570974","https://openalex.org/W2603381882","https://openalex.org/W2945475639"],"abstract_inverted_index":{"For":[0,134],"a":[1,12,41,46,59,69,92,105,135],"large":[2,13],"and":[3,35,84,90,113,197],"complex":[4],"software":[5],"system,":[6],"the":[7,28,100,119,125,131,145,167,174,178,188],"project":[8],"team":[9],"could":[10,21],"receive":[11],"number":[14],"of":[15,48,87,111,121,158],"bug":[16,19,44,66,71,88,96,115,137,156],"reports.":[17,116],"Some":[18],"reports":[20,67,89,97,143,157,182],"be":[22],"duplicates":[23],"as":[24],"they":[25],"essentially":[26],"report":[27],"same":[29],"problem.":[30],"It":[31],"is":[32,45,74,170,183],"often":[33],"tedious":[34],"costly":[36],"to":[37,78],"manually":[38],"check":[39],"if":[40],"newly":[42],"reported":[43,51],"duplicate":[47,65,112,142],"an":[49],"already":[50],"bug.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,139],"propose":[57,91],"BugSim,":[58],"method":[60,169],"that":[61,166,192],"can":[62],"automatically":[63],"retrieve":[64,140],"given":[68],"new":[70,136],"report.":[72],"BugSim":[73,150,186],"based":[75,98],"on":[76,99],"learning":[77],"rank":[79],"concepts.":[80],"We":[81,102,117,148],"identify":[82],"textual":[83],"statistical":[85],"features":[86,122],"similarity":[93],"function":[94],"for":[95,177],"features.":[101],"then":[103],"construct":[104],"training":[106,132],"set":[107],"by":[108,123],"assembling":[109],"pairs":[110],"non-duplicate":[114],"train":[118],"weights":[120],"applying":[124],"stochastic":[126],"gradient":[127],"descent":[128],"algorithm":[129],"over":[130],"set.":[133],"report,":[138],"candidate":[141],"using":[144,151,195],"trained":[146],"model.":[147],"evaluate":[149],"more":[152],"than":[153],"45,100":[154],"real":[155],"twelve":[159],"Eclipse":[160],"projects.":[161],"The":[162],"evaluation":[163],"results":[164],"show":[165],"proposed":[168],"effective.":[171],"On":[172],"average,":[173],"recall":[175],"rate":[176],"top":[179],"10":[180],"retrieved":[181],"76.11%.":[184],"Furthermore,":[185],"outperforms":[187],"previous":[189],"state-of-art":[190],"methods":[191],"are":[193],"implemented":[194],"SVM":[196],"BM25Fext.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}