{"id":"https://openalex.org/W3085258507","doi":"https://doi.org/10.1109/access.2020.2968391","title":"Duplicate Question Detection With Deep Learning in Stack Overflow","display_name":"Duplicate Question Detection With Deep Learning in Stack Overflow","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3085258507","doi":"https://doi.org/10.1109/access.2020.2968391","mag":"3085258507"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2968391","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2968391","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2020.2968391","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100652853","display_name":"Liting Wang","orcid":"https://orcid.org/0000-0002-1215-9495"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liting Wang","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1215-9495","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114585361","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0002-2258-5893"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2258-5893","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044562617","display_name":"Jing Jiang","orcid":"https://orcid.org/0000-0002-6582-0654"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Jiang","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":5.0114,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":{"value":0.96081737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"25964","last_page":"25975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9983000159263611,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8511216640472412},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.8060173392295837},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7500430345535278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7481499910354614},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6250514984130859},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5997925996780396},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4690808653831482},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4396989643573761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33654525876045227},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32630836963653564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8511216640472412},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8060173392295837},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7500430345535278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7481499910354614},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6250514984130859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5997925996780396},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4690808653831482},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4396989643573761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33654525876045227},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32630836963653564},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2968391","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2968391","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a83564ab1c81425a99f90201e9bc2886","is_oa":true,"landing_page_url":"https://doaj.org/article/a83564ab1c81425a99f90201e9bc2886","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 25964-25975 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2968391","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2968391","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G2782398049","display_name":null,"funder_award_id":"2018AAA0102304","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G502157457","display_name":null,"funder_award_id":"61672078","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G663199051","display_name":null,"funder_award_id":"SKLSDE-2019ZX-05","funder_id":"https://openalex.org/F4320326978","funder_display_name":"State Key Laboratory of Software Development Environment"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1614298861","https://openalex.org/W1880262756","https://openalex.org/W1906699800","https://openalex.org/W1970689298","https://openalex.org/W1992984099","https://openalex.org/W2035720976","https://openalex.org/W2062227835","https://openalex.org/W2086530517","https://openalex.org/W2110166424","https://openalex.org/W2139270835","https://openalex.org/W2143612262","https://openalex.org/W2145349611","https://openalex.org/W2147152072","https://openalex.org/W2154774499","https://openalex.org/W2156833313","https://openalex.org/W2163605009","https://openalex.org/W2165022036","https://openalex.org/W2166183437","https://openalex.org/W2167630669","https://openalex.org/W2239327973","https://openalex.org/W2251558607","https://openalex.org/W2401290433","https://openalex.org/W2511803001","https://openalex.org/W2513738415","https://openalex.org/W2560823834","https://openalex.org/W2740130862","https://openalex.org/W2788504331","https://openalex.org/W2894747149","https://openalex.org/W2908092214","https://openalex.org/W2910750801","https://openalex.org/W2911964244","https://openalex.org/W2944955910","https://openalex.org/W2950577311","https://openalex.org/W2955224058","https://openalex.org/W2998277008","https://openalex.org/W2998704965","https://openalex.org/W4231510805","https://openalex.org/W4294170691","https://openalex.org/W4399647672","https://openalex.org/W6636510571","https://openalex.org/W6639619044","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6684191040","https://openalex.org/W6869608176"],"related_works":["https://openalex.org/W2980729574","https://openalex.org/W1560851690","https://openalex.org/W3092047717","https://openalex.org/W4390881630","https://openalex.org/W2770162183","https://openalex.org/W4226493464","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3008584592"],"abstract_inverted_index":{"Stack":[0,30,109,159],"Overflow":[1,31],"is":[2],"a":[3],"popular":[4],"Community-based":[5],"Question":[6],"Answer":[7],"(CQA)":[8],"website":[9],"focused":[10],"on":[11,148,217],"software":[12],"programming":[13],"and":[14,18,32,49,99,131,143,152,166,180,182,190,197,209,225,234],"has":[15],"attracted":[16],"more":[17,19],"users":[20,39,52],"in":[21,29,108,158,192,229],"recent":[22],"years.":[23],"However,":[24],"duplicate":[25,44,65,106,156],"questions":[26,107,157],"frequently":[27],"appear":[28],"they":[33],"are":[34,69,146],"manually":[35],"marked":[36],"by":[37],"the":[38,83,118,200],"with":[40,53],"high":[41,54],"reputation.":[42,55],"Automatic":[43],"question":[45],"detection":[46],"alleviates":[47],"labor":[48],"effort":[50],"for":[51],"Although":[56],"existing":[57],"approaches":[58,68,140,175,186,206,215],"extract":[59],"textual":[60],"features":[61],"to":[62,104,116,154],"automatically":[63],"detect":[64,105,155],"questions,":[66],"these":[67],"limited":[70],"since":[71],"semantic":[72,127],"information":[73,128],"could":[74],"be":[75],"lost.":[76],"To":[77],"tackle":[78],"this":[79],"problem,":[80],"we":[81,113,135],"explore":[82],"use":[84,114],"of":[85,121,194,231],"powerful":[86],"deep":[87,138,184],"learning":[88,139,185,214],"techniques,":[89],"including":[90],"Convolutional":[91],"Neural":[92,96],"Networks":[93,97],"(CNN),":[94],"Recurrent":[95],"(RNN)":[98],"Long":[100],"Short-Term":[101],"Memory":[102],"(LSTM),":[103],"Overflow.":[110,160],"In":[111],"addition,":[112],"Word2Vec":[115],"obtain":[117],"vector":[119],"representations":[120],"words.":[122],"They":[123],"can":[124],"fully":[125],"capture":[126],"at":[129],"document-level":[130],"word-level":[132],"respectively.":[133],"Therefore,":[134],"construct":[136],"three":[137,183],"WV-CNN,":[141,207],"WV-RNN":[142],"WV-LSTM,":[144],"which":[145],"based":[147,216],"Word2Vec,":[149],"CNN,":[150],"RNN":[151],"LSTM,":[153],"Evaluation":[161],"results":[162,202],"show":[163],"that":[164,204],"WV-CNN":[165],"WV-LSTM":[167,210],"have":[168],"made":[169],"significant":[170],"improvements":[171],"over":[172],"four":[173,212],"baseline":[174],"(i.e.,":[176,187],"DupPredictor,":[177],"Dupe,":[178],"DupPredictorRep-T,":[179],"DupeRep)":[181],"DQ-CNN,":[188],"DQ-RNN,":[189],"DQ-LSTM)":[191],"terms":[193,230],"recall-rate@5,":[195,232],"recall-rate@10":[196,233],"recall-rate@20.":[198,235],"Furthermore,":[199],"experimental":[201],"indicate":[203],"our":[205],"WV-RNN,":[208],"outperform":[211],"machine":[213],"Support":[218],"Vector":[219],"Machine,":[220],"Logic":[221],"Regression,":[222],"Random":[223],"Forest":[224],"eXtreme":[226],"Gradient":[227],"Boosting":[228]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}