{"id":"https://openalex.org/W2102776287","doi":"https://doi.org/10.1145/1557019.1557070","title":"Genre-based decomposition of email class noise","display_name":"Genre-based decomposition of email class noise","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2102776287","doi":"https://doi.org/10.1145/1557019.1557070","mag":"2102776287"},"language":"en","primary_location":{"id":"doi:10.1145/1557019.1557070","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and 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/A5111761879","display_name":"Aleksander Ko\u0142cz","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aleksander Kolcz","raw_affiliation_strings":["Microsoft, Redmond, USA","Microsoft Redmond, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084091807","display_name":"Gordon V. Cormack","orcid":"https://orcid.org/0000-0002-5890-0293"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gordon V. Cormack","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"427","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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":1.0,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991999864578247,"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":0.750629186630249},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6638992428779602},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6432907581329346},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5607917904853821},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5420568585395813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4923349618911743},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4361780285835266},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43132591247558594},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.41739344596862793},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38167139887809753},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.29829132556915283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750629186630249},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6638992428779602},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6432907581329346},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5607917904853821},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5420568585395813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4923349618911743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4361780285835266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43132591247558594},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.41739344596862793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38167139887809753},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.29829132556915283},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1557019.1557070","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W171854839","https://openalex.org/W176125184","https://openalex.org/W1485321296","https://openalex.org/W1570501271","https://openalex.org/W1648885110","https://openalex.org/W1666146316","https://openalex.org/W1666942233","https://openalex.org/W1898031563","https://openalex.org/W2041597619","https://openalex.org/W2058737869","https://openalex.org/W2061989622","https://openalex.org/W2104290684","https://openalex.org/W2133002765","https://openalex.org/W2147891303","https://openalex.org/W2155653793","https://openalex.org/W2170892895","https://openalex.org/W2172059508","https://openalex.org/W2293768274","https://openalex.org/W2736182440","https://openalex.org/W2916045930","https://openalex.org/W3100570787","https://openalex.org/W4297970707"],"related_works":["https://openalex.org/W2327107878","https://openalex.org/W2171117985","https://openalex.org/W1526760723","https://openalex.org/W2012356576","https://openalex.org/W2126659863","https://openalex.org/W3112120395","https://openalex.org/W4385670989","https://openalex.org/W774601707","https://openalex.org/W3011514165","https://openalex.org/W2162374031"],"abstract_inverted_index":{"Corruption":[0],"of":[1,16,103],"data":[2,17],"by":[3],"class-label":[4],"noise":[5,25,44,59,70],"is":[6,29,36],"an":[7],"important":[8],"practical":[9],"concern":[10],"impacting":[11],"many":[12],"classification":[13],"problems.":[14],"Studies":[15],"cleaning":[18],"techniques":[19,72],"often":[20],"assume":[21],"a":[22],"uniform":[23],"label":[24,43,87],"model,":[26],"however,":[27],"which":[28],"seldom":[30],"realized":[31],"in":[32,88,99],"practice.":[33],"Relatively":[34],"little":[35],"understood,":[37],"as":[38],"to":[39,78,86,109,118],"how":[40],"the":[41,128,133],"natural":[42],"distribution":[45],"can":[46,60,95,114],"be":[47,96,116],"measured":[48],"or":[49],"simulated.":[50],"Using":[51],"email":[52],"spam-filtering":[53],"data,":[54],"we":[55,106],"demonstrate":[56,68],"that":[57,69,81,92,111],"class":[58],"have":[61],"substantial":[62],"content":[63],"specific":[64],"bias.":[65],"We":[66,90],"also":[67,115],"detection":[71],"based":[73],"on":[74],"classifier":[75],"confidence":[76],"tend":[77],"identify":[79],"instances":[80],"human":[82],"assessors":[83],"are":[84,107],"likely":[85],"error.":[89],"show":[91,110],"genre":[93,112],"modeling":[94],"very":[97],"informative":[98],"identifying":[100],"potential":[101],"areas":[102],"mislabeling.":[104],"Moreover,":[105],"able":[108],"decomposition":[113],"used":[117],"substantially":[119],"improve":[120],"spam":[121],"filtering":[122],"accuracy,":[123],"with":[124],"our":[125],"results":[126],"outperforming":[127],"best":[129],"published":[130],"figures":[131],"for":[132],"trec05-p1":[134],"and":[135],"ceas-2008":[136],"benchmark":[137],"collections.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}