{"id":"https://openalex.org/W2142113519","doi":"https://doi.org/10.1145/1081870.1081934","title":"Scalable discovery of hidden emails from large folders","display_name":"Scalable discovery of hidden emails from large folders","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2142113519","doi":"https://doi.org/10.1145/1081870.1081934","mag":"2142113519"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049259877","display_name":"Giuseppe Carenini","orcid":"https://orcid.org/0000-0003-4310-0119"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Giuseppe Carenini","raw_affiliation_strings":["University of British Columbia, Canada","University of British Columbia, Canada ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia, Canada ,","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113567130","display_name":"Raymond T. Ng","orcid":"https://orcid.org/0000-0003-3692-8524"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Raymond T. Ng","raw_affiliation_strings":["University of British Columbia, Canada","University of British Columbia, Canada ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia, Canada ,","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108423191","display_name":"Xiaodong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaodong Zhou","raw_affiliation_strings":["University of British Columbia, Canada","University of British Columbia, Canada ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia, Canada ,","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"544","last_page":"549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.996999979019165,"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/T11644","display_name":"Spam and Phishing Detection","score":0.996999979019165,"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/T12607","display_name":"Personal Information Management and User Behavior","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.98580002784729,"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":0.830632209777832},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8248332738876343},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6589595079421997},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.545613169670105},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5124743580818176},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4850148856639862},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4489806592464447},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43030795454978943},{"id":"https://openalex.org/keywords/electronic-mail","display_name":"Electronic mail","score":0.41898104548454285},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17240864038467407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830632209777832},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8248332738876343},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6589595079421997},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.545613169670105},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5124743580818176},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4850148856639862},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4489806592464447},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43030795454978943},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.41898104548454285},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17240864038467407},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1081870.1081934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.137.2574","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.137.2574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ubc.ca/~rng/psdepository/sigkdd2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W163605501","https://openalex.org/W1504070272","https://openalex.org/W1535524350","https://openalex.org/W1603920809","https://openalex.org/W1968070828","https://openalex.org/W2007893274","https://openalex.org/W2048392812","https://openalex.org/W2052054518","https://openalex.org/W2085487866","https://openalex.org/W2092013891","https://openalex.org/W2107707985","https://openalex.org/W2110920860","https://openalex.org/W2118744442","https://openalex.org/W2128672521","https://openalex.org/W2137560895","https://openalex.org/W2139472978","https://openalex.org/W4285719527","https://openalex.org/W6722377033"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W2518037665","https://openalex.org/W4242223894","https://openalex.org/W4306886878"],"abstract_inverted_index":{"The":[0,85],"popularity":[1],"of":[2,19,42,89,130],"email":[3,24,47,51,60,98,138,162],"has":[4,29,53],"triggered":[5],"researchers":[6],"to":[7,11],"look":[8],"for":[9,94,108],"ways":[10],"help":[12],"users":[13],"better":[14],"organize":[15],"the":[16,38,70,113,121,126,135],"enormous":[17],"amount":[18],"information":[20],"stored":[21],"in":[22,34,56,61,69,117,148,159],"their":[23],"folders.":[25,163],"One":[26],"challenge":[27],"that":[28,52,143,149,153],"not":[30,66],"been":[31,54,76,83],"studied":[32],"extensively":[33],"text":[35],"mining":[36],"is":[37,48,92],"identification":[39],"and":[40,87,101,128,151],"reconstruction":[41,88],"hidden":[43,46,90,110,144],"emails.":[44],"A":[45],"an":[49],"original":[50],"quoted":[55],"at":[57],"least":[58],"one":[59],"a":[62,106],"folder,":[63],"but":[64],"does":[65],"present":[67],"itself":[68],"same":[71],"folder.":[72],"It":[73],"may":[74,80],"have":[75,82],"(un)intentionally":[77],"deleted":[78],"or":[79],"never":[81],"received.":[84],"discovery":[86],"emails":[91,111,145],"critical":[93],"many":[95],"applications":[96],"including":[97],"classification,":[99],"summarization":[100],"forensics.":[102],"This":[103],"paper":[104],"proposes":[105],"framework":[107,132],"reconstructing":[109],"using":[112,134],"embedded":[114],"quotations":[115],"found":[116],"messages":[118],"further":[119],"down":[120],"thread":[122],"hierarchy.":[123],"We":[124],"evaluate":[125],"robustness":[127],"scalability":[129],"our":[131,154],"by":[133],"Enron":[136],"public":[137],"corpus.":[139],"Our":[140],"experiments":[141],"show":[142],"exist":[146],"widely":[147],"corpus":[150],"also":[152],"optimization":[155],"techniques":[156],"are":[157],"effective":[158],"processing":[160],"large":[161]},"counts_by_year":[{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}