{"id":"https://openalex.org/W2604420197","doi":"https://doi.org/10.1145/3038912.3052701","title":"Detecting Duplicate Posts in Programming QA Communities via Latent Semantics and Association Rules","display_name":"Detecting Duplicate Posts in Programming QA Communities via Latent Semantics and Association Rules","publication_year":2017,"publication_date":"2017-04-03","ids":{"openalex":"https://openalex.org/W2604420197","doi":"https://doi.org/10.1145/3038912.3052701","mag":"2604420197"},"language":"en","primary_location":{"id":"doi:10.1145/3038912.3052701","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3038912.3052701","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3038912.3052701","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070697660","display_name":"Wei Emma Zhang","orcid":"https://orcid.org/0000-0002-0406-5974"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Wei Emma Zhang","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080744092","display_name":"Quan Z. Sheng","orcid":"https://orcid.org/0000-0002-3326-4147"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quan Z. Sheng","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032767467","display_name":"Jey Han Lau","orcid":"https://orcid.org/0000-0002-1647-4628"},"institutions":[{"id":"https://openalex.org/I4210120068","display_name":"IBM Research - Australia","ror":"https://ror.org/027r3nx49","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210120068"]},{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jey Han Lau","raw_affiliation_strings":["The University of Melbourne & IBM Research Australia, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne & IBM Research Australia, Melbourne, Australia","institution_ids":["https://openalex.org/I4210120068","https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005140412","display_name":"Ermyas Abebe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120068","display_name":"IBM Research - Australia","ror":"https://ror.org/027r3nx49","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210120068"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ermyas Abebe","raw_affiliation_strings":["IBM Research Australia, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"IBM Research Australia, Melbourne, Australia","institution_ids":["https://openalex.org/I4210120068"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070697660"],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":7.0599,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97474137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1221","last_page":"1229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9977999925613403,"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":0.8563755750656128},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.698910117149353},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6109669804573059},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5519591569900513},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5363389849662781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49700334668159485},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48871350288391113},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.44750791788101196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43237584829330444},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4219714105129242},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32869231700897217},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15185537934303284},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09810903668403625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8563755750656128},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.698910117149353},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6109669804573059},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5519591569900513},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5363389849662781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49700334668159485},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48871350288391113},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.44750791788101196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43237584829330444},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4219714105129242},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32869231700897217},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15185537934303284},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09810903668403625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3038912.3052701","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3038912.3052701","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3038912.3052701","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3038912.3052701","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on World Wide Web","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1906699800","https://openalex.org/W1975809876","https://openalex.org/W1980095184","https://openalex.org/W1985258161","https://openalex.org/W1999484828","https://openalex.org/W2008056655","https://openalex.org/W2008652694","https://openalex.org/W2035363410","https://openalex.org/W2038721957","https://openalex.org/W2060758175","https://openalex.org/W2086530517","https://openalex.org/W2091825929","https://openalex.org/W2113242816","https://openalex.org/W2119168550","https://openalex.org/W2120284981","https://openalex.org/W2123246351","https://openalex.org/W2124940540","https://openalex.org/W2129018774","https://openalex.org/W2131744502","https://openalex.org/W2151280665","https://openalex.org/W2153579005","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2160218441","https://openalex.org/W2239327973","https://openalex.org/W2250225488","https://openalex.org/W2282146481","https://openalex.org/W2293877768","https://openalex.org/W2340381866","https://openalex.org/W2400323868","https://openalex.org/W2401290433","https://openalex.org/W2950133940","https://openalex.org/W2963514026","https://openalex.org/W3009009611","https://openalex.org/W3085162807","https://openalex.org/W4235505822","https://openalex.org/W6843735874"],"related_works":["https://openalex.org/W3207693618","https://openalex.org/W207304934","https://openalex.org/W2773616286","https://openalex.org/W5053386","https://openalex.org/W69953359","https://openalex.org/W4375928482","https://openalex.org/W4377703168","https://openalex.org/W4308235822","https://openalex.org/W3160627956","https://openalex.org/W2368388617"],"abstract_inverted_index":{"Programming":[0],"community-based":[1],"question-answering":[2,69],"(PCQA)":[3],"websites":[4,71],"such":[5],"as":[6,80,115],"Stack":[7,35,220],"Overflow":[8,36,221],"enable":[9],"programmers":[10],"to":[11,15,43,55,74,78,107,192,226],"find":[12],"working":[13],"solutions":[14],"their":[16],"questions.":[17,47,110],"Despite":[18],"detailed":[19],"posting":[20],"guidelines,":[21],"duplicate":[22,46,57,62,109,149,169,217],"questions":[23,58,150,162,218],"that":[24,145,179],"have":[25,209],"been":[26],"answered":[27],"are":[28,72],"frequently":[29,147],"created.":[30],"To":[31,122],"tackle":[32],"this":[33,96],"problem,":[34],"provides":[37],"a":[38,50,100,116,165,173,196,211],"mechanism":[39],"for":[40,103,125,168],"reputable":[41],"users":[42],"manually":[44],"mark":[45],"This":[48],"is":[49,88],"laborious":[51],"effort,":[52],"and":[53,142,163,222],"leads":[54],"many":[56],"remain":[59],"undetected.":[60],"Existing":[61],"detection":[63,114],"methodologies":[64],"from":[65,92,134,216],"traditional":[66],"community":[67],"based":[68],"(CQA)":[70],"difficult":[73],"be":[75],"adopted":[76],"directly":[77],"PCQA,":[79],"PCQA":[81,105],"posts":[82],"often":[83],"contain":[84],"source":[85],"code":[86],"which":[87],"linguistically":[89],"very":[90,183],"different":[91],"natural":[93],"languages.":[94],"In":[95],"paper,":[97],"we":[98,208],"propose":[99],"methodology":[101,129],"designed":[102],"the":[104,113,135,201,204,224,227],"domain":[106],"detect":[108],"We":[111],"model":[112,140],"classification":[117],"problem":[118],"over":[119,188],"question":[120,126],"pairs.":[121],"extract":[123],"features":[124,141,157],"pairs,":[127],"our":[128,180],"leverages":[130],"continuous":[131],"word":[132],"vectors":[133],"deep":[136],"learning":[137],"literature,":[138],"topic":[139],"phrases":[143,215],"pairs":[144],"co-occur":[146],"in":[148,185],"mined":[151,210],"using":[152],"machine":[153],"translation":[154],"systems.":[155],"These":[156],"capture":[158],"semantic":[159],"similarities":[160],"between":[161],"produce":[164],"strong":[166],"performance":[167],"detection.":[170],"Experiments":[171],"on":[172,219],"range":[174],"of":[175,198,200,213],"real-world":[176],"datasets":[177],"demonstrate":[178],"method":[181],"works":[182],"well;":[184],"some":[186],"cases":[187],"30%":[189],"improvement":[190],"compared":[191],"state-of-the-art":[193],"benchmarks.":[194],"As":[195],"product":[197],"one":[199],"proposed":[202],"features,":[203],"association":[205],"score":[206],"feature,":[207],"set":[212],"associated":[214],"open":[223],"dataset":[225],"public.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}