{"id":"https://openalex.org/W3009517030","doi":"https://doi.org/10.1145/3379597.3387443","title":"PUMiner","display_name":"PUMiner","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W3009517030","doi":"https://doi.org/10.1145/3379597.3387443","mag":"3009517030"},"language":"en","primary_location":{"id":"doi:10.1145/3379597.3387443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.03741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Triet Huynh Minh Le","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Triet Huynh Minh Le","raw_affiliation_strings":["School of Computer Science, The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"David Hin","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Hin","raw_affiliation_strings":["School of Computer Science, The University of Adelaide, Adelaide, Australia and Cyber Security Cooperative Research Centre"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Adelaide, Adelaide, Australia and Cyber Security Cooperative Research Centre","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Roland Croft","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roland Croft","raw_affiliation_strings":["School of Computer Science, The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":null,"display_name":"M. Ali Babar","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"M. Ali Babar","raw_affiliation_strings":["School of Computer Science, The University of Adelaide, Adelaide, Australia and Cyber Security Cooperative Research Centre"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Adelaide, Adelaide, Australia and Cyber Security Cooperative Research Centre","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":1.1499,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81849235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"361"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9958000183105469,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9940999746322632,"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/matching","display_name":"Matching (statistics)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4823000133037567},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46880000829696655},{"id":"https://openalex.org/keywords/information-security","display_name":"Information security","score":0.3700999915599823},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.35929998755455017},{"id":"https://openalex.org/keywords/computer-security-model","display_name":"Computer security model","score":0.35679998993873596},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3540000021457672},{"id":"https://openalex.org/keywords/software-security-assurance","display_name":"Software security assurance","score":0.31299999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6836000084877014},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38339999318122864},{"id":"https://openalex.org/C527648132","wikidata":"https://www.wikidata.org/wiki/Q189900","display_name":"Information security","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C121822524","wikidata":"https://www.wikidata.org/wiki/Q5157582","display_name":"Computer security model","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C62913178","wikidata":"https://www.wikidata.org/wiki/Q7554361","display_name":"Software security assurance","level":4,"score":0.31299999356269836},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C38369872","wikidata":"https://www.wikidata.org/wiki/Q7445009","display_name":"Security analysis","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C10511746","wikidata":"https://www.wikidata.org/wiki/Q899388","display_name":"Data security","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3379597.3387443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.03741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03741","pdf_url":"https://arxiv.org/pdf/2003.03741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/129195","is_oa":false,"landing_page_url":"http://hdl.handle.net/2440/129195","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://dl.acm.org/doi/proceedings/10.1145/3379597","raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.03741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03741","pdf_url":"https://arxiv.org/pdf/2003.03741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W9328536","https://openalex.org/W22461475","https://openalex.org/W208128215","https://openalex.org/W1480376833","https://openalex.org/W1972978214","https://openalex.org/W1979504415","https://openalex.org/W1985258161","https://openalex.org/W2050871273","https://openalex.org/W2056894403","https://openalex.org/W2060758175","https://openalex.org/W2093400716","https://openalex.org/W2098162425","https://openalex.org/W2133227149","https://openalex.org/W2511548333","https://openalex.org/W2738381526","https://openalex.org/W2748690817","https://openalex.org/W4239510810","https://openalex.org/W6630177651","https://openalex.org/W6639619044","https://openalex.org/W6640462745","https://openalex.org/W6675354045","https://openalex.org/W6679539681","https://openalex.org/W6845883598"],"related_works":[],"abstract_inverted_index":{"Security":[0,135],"is":[1,69,141,162,212,224],"an":[2,42,188],"increasing":[3],"concern":[4],"in":[5],"software":[6],"development.":[7],"Developer":[8],"Question":[9],"and":[10,101,116,131,165,174,236,245],"Answer":[11],"(Q&A)":[12],"websites":[13,242],"provide":[14,233],"a":[15,76,91,104,218],"large":[16],"amount":[17],"of":[18,45,98,147,160,190,203,221],"security":[19,29,47,84,110,238],"discussion.":[20],"Existing":[21],"studies":[22],"have":[23],"used":[24],"human-defined":[25],"rules":[26],"to":[27,41,72,81,95,108,208],"mine":[28,83],"discussions,":[30],"but":[31],"these":[32],"works":[33],"still":[34,216],"miss":[35],"many":[36],"posts,":[37,100,181],"which":[38,223],"may":[39],"lead":[40],"incomplete":[43],"analysis":[44],"the":[46,60,64,99,113,144,201,204,209,234],"practices":[48],"reported":[49],"on":[50,122,128,134,178,240],"Q&A":[51,87,241],"websites.":[52,88],"Traditional":[53],"supervised":[54],"Machine":[55],"Learning":[56],"methods":[57],"can":[58],"automate":[59],"mining":[61],"process;":[62],"however,":[63],"required":[65],"negative":[66],"(non-security)":[67],"class":[68],"too":[70],"expensive":[71],"obtain.":[73],"We":[74,119,137],"propose":[75],"novel":[77],"learning":[78],"framework,":[79],"PUMiner,":[80,231],"automatically":[82],"posts":[85,127,133,207],"from":[86],"PUMiner":[89,121,140,161,183,215],"builds":[90],"context-aware":[92],"embedding":[93],"model":[94,107,153],"extract":[96],"features":[97],"then":[102],"develops":[103],"two-stage":[105],"PU":[106,176],"identify":[109],"content":[111,239],"using":[112],"labelled":[114,205],"Positive":[115],"Un-labelled":[117],"posts.":[118],"evaluate":[120],"more":[123],"than":[124,169,227],"17.2":[125],"million":[126],"Stack":[129],"Overflow":[130],"52,611":[132],"StackExchange.":[136],"show":[138],"that":[139],"effective":[142],"with":[143,187],"validation":[145],"performance":[146],"at":[148],"least":[149],"0.85":[150],"across":[151],"all":[152],"configurations.":[154],"Moreover,":[155],"Matthews":[156],"Correlation":[157],"Coefficient":[158],"(MCC)":[159],"0.906,":[163],"0.534":[164],"0.084":[166],"points":[167],"higher":[168],"one-class":[170],"SVM,":[171],"positive-similarity":[172],"filtering,":[173],"one-stage":[175],"models":[177],"unseen":[179],"testing":[180],"respectively.":[182],"also":[184],"performs":[185],"well":[186],"MCC":[189,220],"0.745":[191],"for":[192,243],"scenarios":[193],"where":[194],"string":[195],"matching":[196],"totally":[197],"fails.":[198],"Even":[199],"when":[200],"ratio":[202],"positive":[206],"un-labelled":[210],"ones":[211],"only":[213],"1:100,":[214],"achieves":[217],"strong":[219],"0.65,":[222],"160%":[225],"better":[226],"fully-supervised":[228],"learning.":[229],"Using":[230],"we":[232],"largest":[235],"up-to-date":[237],"practitioners":[244],"researchers.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-03-13T00:00:00"}