{"id":"https://openalex.org/W2063410300","doi":"https://doi.org/10.1109/compsacw.2010.45","title":"Natural Language Processing Based Detection of Duplicate Defect Patterns","display_name":"Natural Language Processing Based Detection of Duplicate Defect Patterns","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2063410300","doi":"https://doi.org/10.1109/compsacw.2010.45","mag":"2063410300"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsacw.2010.45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5103089964","display_name":"Qian Wu","orcid":"https://orcid.org/0000-0002-0612-0287"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"funder","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wu","raw_affiliation_strings":["[Key Lab. of High Confidence Software Technol., Peking Univ., Beijing, China]"],"affiliations":[{"raw_affiliation_string":"[Key Lab. of High Confidence Software Technol., Peking Univ., Beijing, China]","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012567911","display_name":"Qianxiang Wang","orcid":"https://orcid.org/0000-0002-6598-0041"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"funder","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxiang Wang","raw_affiliation_strings":["[Key Lab. of High Confidence Software Technol., Peking Univ., Beijing, China]"],"affiliations":[{"raw_affiliation_string":"[Key Lab. of High Confidence Software Technol., Peking Univ., Beijing, China]","institution_ids":["https://openalex.org/I20231570"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.39,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":5,"citation_normalized_percentile":{"value":0.655401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":79,"max":81},"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"225"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9999,"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":0.9999,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9952,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9934,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/software-bug","display_name":"Software bug","score":0.4567311}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000404},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6129999},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5286931},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46727788},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.4567311},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44482902},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40869638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3489952},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3297904},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20709145},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsacw.2010.45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.48}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1531717019","https://openalex.org/W1584735725","https://openalex.org/W1956559956","https://openalex.org/W1986453394","https://openalex.org/W1989338554","https://openalex.org/W2043811931","https://openalex.org/W2054520963","https://openalex.org/W2061504872","https://openalex.org/W2074297512","https://openalex.org/W2098230348","https://openalex.org/W2109612250","https://openalex.org/W2111949697","https://openalex.org/W2124666592","https://openalex.org/W2128158689","https://openalex.org/W2156833313","https://openalex.org/W2165022036","https://openalex.org/W2183151968","https://openalex.org/W2285056549","https://openalex.org/W2325227998","https://openalex.org/W4233832762","https://openalex.org/W4298304654"],"related_works":["https://openalex.org/W4310225030","https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2494338568","https://openalex.org/W2158836806","https://openalex.org/W2132641928","https://openalex.org/W2122678784","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W1495042958"],"abstract_inverted_index":{"A":[0],"Defect":[1,23],"pattern":[2,46,116],"repository":[3],"collects":[4],"different":[5],"kinds":[6],"of":[7,14,17,42,59,132,148],"defect":[8,32,45,53,115],"patterns,":[9],"which":[10],"are":[11,120,134],"general":[12],"descriptions":[13],"the":[15,40,68,102,108,113,149,157],"characteristics":[16],"commonly":[18],"occurring":[19],"software":[20],"code":[21],"defects.":[22],"patterns":[24,54,61],"can":[25],"be":[26],"widely":[27],"used":[28],"by":[29,136],"programmers,":[30],"static":[31],"analysis":[33],"tools,":[34],"and":[35,95,105],"even":[36],"runtime":[37],"verification.":[38],"Following":[39],"idea":[41],"web":[43],"2.0,":[44],"repositories":[47],"allow":[48],"these":[49],"users":[50],"to":[51,64,75,100,111,122,127],"submit":[52],"they":[55],"found.":[56],"However,":[57],"submission":[58],"duplicate":[60],"would":[62],"lead":[63],"a":[65],"redundancy":[66],"in":[67,153,156],"repository.":[69,158],"This":[70],"paper":[71],"introduces":[72],"an":[73],"approach":[74,85,125,144],"suggest":[76],"potential":[77],"duplicates":[78,133,151],"based":[79,90],"on":[80,91],"natural":[81],"language":[82],"processing.":[83],"Our":[84],"first":[86],"computes":[87],"field":[88,103,109],"similarities":[89,110],"Vector":[92],"Space":[93],"Model,":[94],"then":[96],"employs":[97],"Information":[98],"Entropy":[99],"determine":[101],"importance,":[104],"next":[106],"combines":[107],"form":[112],"final":[114],"similarity.":[117],"Two":[118],"strategies":[119],"introduced":[121],"make":[123],"our":[124,143,154],"adaptive":[126],"special":[128],"situations.":[129],"Finally,":[130],"groups":[131],"obtained":[135],"adopting":[137],"Hierarchical":[138],"Clustering.":[139],"Evaluation":[140],"indicates":[141],"that":[142],"could":[145],"detect":[146],"most":[147],"actual":[150],"(72%":[152],"experiment)":[155]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2063410300","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-03-23T15:55:37.147650","created_date":"2016-06-24"}