{"id":"https://openalex.org/W4221037967","doi":"https://doi.org/10.1142/s0218194022500073","title":"Detecting Duplicate Questions in Stack Overflow via Source Code Modeling","display_name":"Detecting Duplicate Questions in Stack Overflow via Source Code Modeling","publication_year":2022,"publication_date":"2022-02-01","ids":{"openalex":"https://openalex.org/W4221037967","doi":"https://doi.org/10.1142/s0218194022500073"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194022500073","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194022500073","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","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/A5017175424","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0001-8084-9386"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Gao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Zhejiang, Hangzhou 310027, P.\u00a0R.\u00a0China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Zhejiang, Hangzhou 310027, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029600413","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-6325-0766"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Zhejiang, Hangzhou 310027, P.\u00a0R.\u00a0China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Zhejiang, Hangzhou 310027, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051512158","display_name":"Guandong Xu","orcid":"https://orcid.org/0000-0003-4493-6663"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guandong Xu","raw_affiliation_strings":["Advanced Analytics Institute, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Advanced Analytics Institute, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017175424"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73024373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":"02","first_page":"227","last_page":"255"},"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.989799976348877,"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":0.8290500640869141},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7008877992630005},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6331486701965332},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5958611965179443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5690698027610779},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5149450898170471},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5131117105484009},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4473688006401062},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4393627643585205},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.41856855154037476},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3780132532119751},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3735305368900299},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35163193941116333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8290500640869141},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7008877992630005},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6331486701965332},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5958611965179443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690698027610779},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5149450898170471},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5131117105484009},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4473688006401062},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4393627643585205},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.41856855154037476},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3780132532119751},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3735305368900299},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35163193941116333},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218194022500073","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194022500073","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1899008360","display_name":null,"funder_award_id":"62176231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3867146099","display_name":null,"funder_award_id":"62106218","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":14,"referenced_works":["https://openalex.org/W2163922914","https://openalex.org/W2239327973","https://openalex.org/W2325227998","https://openalex.org/W2401290433","https://openalex.org/W2513738415","https://openalex.org/W2604272474","https://openalex.org/W2763532355","https://openalex.org/W2884229567","https://openalex.org/W3011131872","https://openalex.org/W3044950360","https://openalex.org/W3085258507","https://openalex.org/W3176804172","https://openalex.org/W4252076394","https://openalex.org/W4256691599"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W4287027380","https://openalex.org/W2789551765","https://openalex.org/W4286432911","https://openalex.org/W2942293597"],"abstract_inverted_index":{"Stack":[0,36,168],"Overflow":[1,37,169],"is":[2,79],"one":[3],"of":[4,17,41,76,95],"the":[5,15,45,63,68,74,83,93,123,150,167],"most":[6],"popular":[7],"Question-Answering":[8],"sites":[9],"for":[10],"programmers.":[11],"However,":[12,58],"it":[13],"faces":[14],"problem":[16],"question":[18,33,46,56,78,97,152,157],"duplication,":[19],"where":[20],"newly":[21],"created":[22],"questions":[23,120,179],"are":[24],"identical":[25],"to":[26,53,91,115,121,133],"previous":[27],"questions.":[28,69],"Existing":[29],"works":[30],"on":[31,44,166,189],"duplicate":[32,55,178],"detection":[34,153],"in":[35,67,71],"extract":[38,116,134],"a":[39,77,96,156],"set":[40],"textual":[42,117],"features":[43,102,118,138],"pairs":[47],"and":[48,103,111,136,171,183,191],"use":[49,108,128],"supervised":[50],"learning":[51,147],"approaches":[52,188],"classify":[54],"pairs.":[57],"they":[59],"do":[60],"not":[61],"consider":[62],"source":[64,84,104,140],"code":[65,105],"information":[66],"While":[70],"some":[72],"cases,":[73],"intention":[75],"mainly":[80],"represented":[81],"by":[82,98,148],"code.":[85,141],"In":[86,142],"this":[87],"paper,":[88],"we":[89,144],"aim":[90],"learn":[92],"semantics":[94],"combining":[99,149],"both":[100],"text":[101],"features.":[106],"We":[107,127,162],"word":[109],"embedding":[110],"convolutional":[112,130],"neural":[113,131],"networks":[114,132],"from":[119,139],"overcome":[122],"lexical":[124],"gap":[125],"issue.":[126],"tree-based":[129],"structural":[135],"semantic":[137],"addition,":[143],"perform":[145],"multi-task":[146],"duplication":[151],"task":[154],"with":[155,180,186],"tag":[158],"prediction":[159],"side":[160],"task.":[161],"conduct":[163],"extensive":[164],"experiments":[165],"dataset":[170],"show":[172],"that":[173],"our":[174],"approach":[175],"can":[176],"detect":[177],"higher":[181],"recall":[182],"MRR":[184],"compared":[185],"baseline":[187],"Python":[190],"Java":[192],"programming":[193],"languages.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
