{"id":"https://openalex.org/W2401290433","doi":"https://doi.org/10.1145/2901739.2901770","title":"Mining duplicate questions in stack overflow","display_name":"Mining duplicate questions in stack overflow","publication_year":2016,"publication_date":"2016-05-14","ids":{"openalex":"https://openalex.org/W2401290433","doi":"https://doi.org/10.1145/2901739.2901770","mag":"2401290433"},"language":"en","primary_location":{"id":"doi:10.1145/2901739.2901770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2901739.2901770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference 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/A5084196686","display_name":"Muhammad Ahasanuzzaman","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Muhammad Ahasanuzzaman","raw_affiliation_strings":["University of Dhaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Dhaka","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027988131","display_name":"Muhammad Asaduzzaman","orcid":"https://orcid.org/0000-0001-9048-7980"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Muhammad Asaduzzaman","raw_affiliation_strings":["University of Saskatchewan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102756770","display_name":"Chanchal K. Roy","orcid":"https://orcid.org/0000-0003-0519-6164"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chanchal K. Roy","raw_affiliation_strings":["University of Saskatchewan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089178328","display_name":"Kevin A. Schneider","orcid":"https://orcid.org/0000-0003-1113-1754"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kevin A. Schneider","raw_affiliation_strings":["University of Saskatchewan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan","institution_ids":["https://openalex.org/I32625721"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":123,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"402","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8238001465797424},{"id":"https://openalex.org/keywords/reputation","display_name":"Reputation","score":0.6337259411811829},{"id":"https://openalex.org/keywords/recall-rate","display_name":"Recall rate","score":0.577183723449707},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5607218146324158},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5059358477592468},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46408841013908386},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4629078805446625},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.43607014417648315},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3792465925216675},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35770052671432495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3097628355026245},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10646328330039978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238001465797424},{"id":"https://openalex.org/C48798503","wikidata":"https://www.wikidata.org/wiki/Q877546","display_name":"Reputation","level":2,"score":0.6337259411811829},{"id":"https://openalex.org/C2987098735","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"Recall rate","level":2,"score":0.577183723449707},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5607218146324158},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5059358477592468},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46408841013908386},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4629078805446625},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.43607014417648315},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3792465925216675},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35770052671432495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3097628355026245},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10646328330039978},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2901739.2901770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2901739.2901770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W142212369","https://openalex.org/W1532325895","https://openalex.org/W1906699800","https://openalex.org/W1981795678","https://openalex.org/W1999484828","https://openalex.org/W1999910737","https://openalex.org/W2012833704","https://openalex.org/W2014755981","https://openalex.org/W2051204868","https://openalex.org/W2056894403","https://openalex.org/W2070488056","https://openalex.org/W2070823011","https://openalex.org/W2072780977","https://openalex.org/W2085922539","https://openalex.org/W2086530517","https://openalex.org/W2099769844","https://openalex.org/W2102114894","https://openalex.org/W2108545456","https://openalex.org/W2110166424","https://openalex.org/W2123246351","https://openalex.org/W2125189744","https://openalex.org/W2139270835","https://openalex.org/W2140887277","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2156833313","https://openalex.org/W2158133897","https://openalex.org/W2163005242","https://openalex.org/W2165022036","https://openalex.org/W2167630669","https://openalex.org/W2170045560","https://openalex.org/W2239327973","https://openalex.org/W2400323868","https://openalex.org/W6668244102"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W1996359983","https://openalex.org/W2601891598","https://openalex.org/W4367460280","https://openalex.org/W4328049145","https://openalex.org/W2121569490","https://openalex.org/W3214249595","https://openalex.org/W2352065863","https://openalex.org/W4387052059","https://openalex.org/W2283349687"],"abstract_inverted_index":{"Stack":[0,99],"Overflow":[1],"is":[2,9],"a":[3,38,88,108,113,125,148,163],"popular":[4],"question":[5,39],"answering":[6],"site":[7,26,52],"that":[8,20,111,131,158,167],"focused":[10],"on":[11,55,102],"programming":[12],"problems.":[13],"Despite":[14],"efforts":[15],"to":[16,34,40,63,91,119],"prevent":[17],"asking":[18],"questions":[19,67,97,129,137],"have":[21],"already":[22,46],"been":[23,47],"answered,":[24],"the":[25],"contains":[27],"duplicate":[28,96,121,136,153],"questions.":[29,122],"This":[30],"may":[31],"cause":[32],"developers":[33],"unnecessarily":[35],"wait":[36],"for":[37,151],"be":[41],"answered":[42],"when":[43],"it":[44],"has":[45,162],"asked":[48],"and":[49,58,155],"answered.":[50],"The":[51],"currently":[53],"depends":[54],"its":[56],"moderators":[57],"users":[59,94],"with":[60,138,146],"high":[61],"reputation":[62],"manually":[64],"mark":[65],"those":[66],"as":[68],"duplicates,":[69],"which":[70],"not":[71],"only":[72],"results":[73],"in":[74,98],"delayed":[75],"responses":[76],"but":[77],"also":[78,142],"requires":[79],"additional":[80],"efforts.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,106,156],"first":[86],"perform":[87],"manual":[89,104],"investigation":[90,105],"understand":[92],"why":[93],"submit":[95],"Overflow.":[100],"Based":[101],"our":[103,132,144,159],"propose":[107],"classification":[109],"technique":[110,133,145,150,161],"uses":[112],"number":[114,127],"of":[115,128],"carefully":[116],"chosen":[117],"features":[118],"identify":[120],"Evaluation":[123],"using":[124],"large":[126],"shows":[130],"can":[134],"detect":[135],"reasonable":[139],"accuracy.":[140],"We":[141],"compare":[143],"DupPredictor,":[147],"state-of-the-art":[149],"detecting":[152],"questions,":[154],"found":[157],"proposed":[160],"better":[164],"recall-rate":[165],"than":[166],"technique.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
