{"id":"https://openalex.org/W4237777282","doi":"https://doi.org/10.7287/peerj.preprints.26555v1","title":"Duplicate Question Detection in Stack Overflow: A Reproducibility Study","display_name":"Duplicate Question Detection in Stack Overflow: A Reproducibility Study","publication_year":2018,"publication_date":"2018-02-21","ids":{"openalex":"https://openalex.org/W4237777282","doi":"https://doi.org/10.7287/peerj.preprints.26555v1"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.26555v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.26555v1","pdf_url":"https://peerj.com/preprints/26555.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://peerj.com/preprints/26555.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026260952","display_name":"Rodrigo F. G. Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I80850581","display_name":"Universidade Federal de Uberl\u00e2ndia","ror":"https://ror.org/04x3wvr31","country_code":"BR","type":"education","lineage":["https://openalex.org/I80850581"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Rodrigo F G Silva","raw_affiliation_strings":["Faculdade de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Uberl\u00e2ndia, Uberl\u00e2ndia, Minas Gerais, Brazil"],"affiliations":[{"raw_affiliation_string":"Faculdade de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Uberl\u00e2ndia, Uberl\u00e2ndia, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I80850581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022372992","display_name":"Kl\u00e9risson V. R. Paix\u00e3o","orcid":"https://orcid.org/0000-0002-8257-5865"},"institutions":[{"id":"https://openalex.org/I80850581","display_name":"Universidade Federal de Uberl\u00e2ndia","ror":"https://ror.org/04x3wvr31","country_code":"BR","type":"education","lineage":["https://openalex.org/I80850581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Klerisson V Paixao","raw_affiliation_strings":["Faculdade de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Uberl\u00e2ndia, Uberl\u00e2ndia, Minas Gerais, Brazil"],"affiliations":[{"raw_affiliation_string":"Faculdade de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Uberl\u00e2ndia, Uberl\u00e2ndia, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I80850581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010173851","display_name":"Marcelo de Almeida Maia","orcid":"https://orcid.org/0000-0003-3578-1380"},"institutions":[{"id":"https://openalex.org/I80850581","display_name":"Universidade Federal de Uberl\u00e2ndia","ror":"https://ror.org/04x3wvr31","country_code":"BR","type":"education","lineage":["https://openalex.org/I80850581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcelo de A. Maia","raw_affiliation_strings":["Faculdade de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Uberl\u00e2ndia, Uberl\u00e2ndia, Minas Gerais, Brazil"],"affiliations":[{"raw_affiliation_string":"Faculdade de Ci\u00eancia da Computa\u00e7\u00e3o, Universidade Federal de Uberl\u00e2ndia, Uberl\u00e2ndia, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I80850581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026260952"],"corresponding_institution_ids":["https://openalex.org/I80850581"],"apc_list":null,"apc_paid":null,"fwci":0.44649252,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78284673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9997000098228455,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9997000098228455,"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":0.9987999796867371,"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":0.9833999872207642,"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":0.7444477081298828},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.7211609482765198},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6552308797836304},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6011781692504883},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5678483843803406},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5496941804885864},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4692677855491638},{"id":"https://openalex.org/keywords/recall-rate","display_name":"Recall rate","score":0.46032655239105225},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.42131394147872925},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3773517608642578},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33196306228637695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2909145951271057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27870672941207886},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.17112326622009277},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.12815886735916138},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.12597930431365967},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12018930912017822},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08909985423088074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08610332012176514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444477081298828},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.7211609482765198},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6552308797836304},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6011781692504883},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5678483843803406},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5496941804885864},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4692677855491638},{"id":"https://openalex.org/C2987098735","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"Recall rate","level":2,"score":0.46032655239105225},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.42131394147872925},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3773517608642578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33196306228637695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2909145951271057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27870672941207886},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17112326622009277},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.12815886735916138},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.12597930431365967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12018930912017822},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08909985423088074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08610332012176514},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.26555v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.26555v1","pdf_url":"https://peerj.com/preprints/26555.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.26555v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.26555v1","pdf_url":"https://peerj.com/preprints/26555.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4237777282.pdf","grobid_xml":"https://content.openalex.org/works/W4237777282.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W1996359983","https://openalex.org/W2601891598","https://openalex.org/W4367460280","https://openalex.org/W2121569490","https://openalex.org/W3214249595","https://openalex.org/W2352065863","https://openalex.org/W2946494454","https://openalex.org/W4387052059","https://openalex.org/W2283349687"],"abstract_inverted_index":{"Stack":[0,20],"Overflow":[1,21],"has":[2,13],"become":[3],"a":[4,93,132],"fundamental":[5],"element":[6],"of":[7,27,31,42,95,108,135,141,148,160],"developer":[8],"toolset.":[9],"Such":[10],"influence":[11],"increase":[12],"been":[14],"accompanied":[15],"by":[16],"an":[17,89],"effort":[18],"from":[19],"community":[22],"to":[23,117,126,171],"keep":[24],"the":[25,32,39,115,146,155],"quality":[26,37],"its":[28],"content.":[29],"One":[30],"problems":[33],"which":[34,83],"jeopardizes":[35],"that":[36,114,154],"is":[38],"continuous":[40],"growth":[41],"duplicated":[43,55,161],"questions.":[44,56],"To":[45],"solve":[46],"this":[47],"problem,":[48],"prior":[49],"works":[50,69,79,157],"focused":[51],"on":[52,85],"automatically":[53],"detecting":[54],"Two":[57],"important":[58],"solutions":[59],"are":[60,121],"DupPredictor":[61,96],"and":[62,97,110,165],"Dupe.":[63,98],"Despite":[64],"reporting":[65],"significant":[66],"results,":[67,100],"both":[68,137],"do":[70],"not":[71,101],"provide":[72],"their":[73,173],"implementations":[74],"publicly":[75],"available,":[76],"hindering":[77],"subsequent":[78,156],"in":[80,139,163],"scientific":[81],"literature":[82],"rely":[84],"them.":[86],"We":[87],"executed":[88],"empirical":[90],"study":[91],"as":[92,145],"reproduction":[94],"Our":[99,151],"robust":[102],"when":[103,124],"attempted":[104],"with":[105],"different":[106],"set":[107],"tools":[109],"data":[111],"sets,":[112],"show":[113],"barriers":[116],"reproduce":[118],"these":[119],"approaches":[120],"high.":[122],"Furthermore,":[123],"applied":[125],"more":[127,169],"recent":[128],"data,":[129],"we":[130],"observe":[131],"performance":[133],"decay":[134],"our":[136],"reproductions":[138],"terms":[140],"recall-rate":[142],"over":[143],"time,":[144],"number":[147],"questions":[149,162],"increases.":[150],"findings":[152],"suggest":[153],"concerning":[158],"detection":[159],"Question":[164],"Answer":[166],"communities":[167],"require":[168],"investigation":[170],"assert":[172],"findings.":[174]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}