{"id":"https://openalex.org/W2150973844","doi":"https://doi.org/10.1145/1081870.1081885","title":"Combining email models for false positive reduction","display_name":"Combining email models for false positive reduction","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2150973844","doi":"https://doi.org/10.1145/1081870.1081885","mag":"2150973844"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081885","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":"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/A5082220966","display_name":"Shlomo Hershkop","orcid":"https://orcid.org/0000-0003-2311-5268"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shlomo Hershkop","raw_affiliation_strings":["Columbia University, New York, NY"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084213178","display_name":"Salvatore J. Stolfo","orcid":"https://orcid.org/0000-0003-1611-0100"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Salvatore J. Stolfo","raw_affiliation_strings":["Columbia University, New York, NY"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082220966"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":15.2649,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.98640091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"107"},"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":0.9975000023841858,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9936000108718872,"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":0.8543604612350464},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.8144794702529907},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5994031429290771},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5701230764389038},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5660222768783569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5116603374481201},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5012612342834473},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44080445170402527},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4246430993080139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543604612350464},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.8144794702529907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5994031429290771},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5701230764389038},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5660222768783569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116603374481201},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5012612342834473},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44080445170402527},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4246430993080139},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":3,"locations":[{"id":"doi:10.1145/1081870.1081885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081885","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:10.1.1.332.1806","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.1806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/kdd05/docs/p98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.83.8686","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.83.8686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/~sh553/publications/kdd05-final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W27046283","https://openalex.org/W47559851","https://openalex.org/W57814663","https://openalex.org/W148103248","https://openalex.org/W1497249636","https://openalex.org/W1504008138","https://openalex.org/W1504070272","https://openalex.org/W1505796919","https://openalex.org/W1511085305","https://openalex.org/W1534477342","https://openalex.org/W1576189261","https://openalex.org/W1594013922","https://openalex.org/W1609518033","https://openalex.org/W1648885110","https://openalex.org/W1912123407","https://openalex.org/W1986944834","https://openalex.org/W1989568037","https://openalex.org/W1993387039","https://openalex.org/W2019580127","https://openalex.org/W2078396547","https://openalex.org/W2084134149","https://openalex.org/W2085302848","https://openalex.org/W2089923329","https://openalex.org/W2093825590","https://openalex.org/W2094705469","https://openalex.org/W2096942889","https://openalex.org/W2107999630","https://openalex.org/W2120011452","https://openalex.org/W2122558050","https://openalex.org/W2143840553","https://openalex.org/W2158275940","https://openalex.org/W2162836724","https://openalex.org/W2169384781","https://openalex.org/W2171622762","https://openalex.org/W2525786140","https://openalex.org/W2561675875","https://openalex.org/W3017143921","https://openalex.org/W3021787434","https://openalex.org/W4239414618","https://openalex.org/W6685009254","https://openalex.org/W6776565550"],"related_works":["https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W3098003361","https://openalex.org/W202723009","https://openalex.org/W2188612292","https://openalex.org/W4206462905","https://openalex.org/W2165396616"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"and":[2,12,123,168,189,207,210,224],"data":[3,21,187],"mining":[4],"can":[5,48,229],"be":[6,88,230],"effectively":[7],"used":[8],"to":[9,32,102,143,182,204,237],"model,":[10],"classify":[11],"discover":[13],"interesting":[14],"information":[15],"for":[16,39,78,106,164,172,232],"a":[17,34,93,145,183,201],"wide":[18,35],"variety":[19],"of":[20,37,58,75,109,130,147,160,175,192,235],"including":[22],"email.":[23,96],"The":[24,218],"Email":[25],"Mining":[26],"Toolkit,":[27],"EMT,":[28],"has":[29,99,116,133],"been":[30,100,117,134],"designed":[31],"provide":[33],"range":[36],"analyses":[38],"arbitrary":[40],"email":[41,83,131,186],"sources.":[42],"Depending":[43],"upon":[44],"the":[45,69,73,107,141,154,173,221,240],"task,":[46],"one":[47,82],"usually":[49],"achieve":[50],"very":[51,94,184],"high":[52],"accuracy,":[53],"but":[54,113],"with":[55,136],"some":[56],"amount":[57],"false":[59,63,170],"positive":[60],"tradeoff.":[61],"Generally":[62],"positives":[64,171],"are":[65],"prohibitively":[66],"expensive":[67],"in":[68,126,153],"real":[70],"world.":[71],"In":[72],"case":[74],"spam":[76,176],"detection,":[77],"example,":[79],"even":[80],"if":[81,90],"is":[84,92],"misclassified,":[85],"this":[86,127],"may":[87],"unacceptable":[89],"it":[91,213],"important":[95],"Much":[97],"work":[98,115],"done":[101],"improve":[103],"specific":[104],"algorithms":[105,122],"task":[108],"detecting":[110],"unwanted":[111],"messages,":[112],"less":[114],"report":[118],"on":[119,196],"leveraging":[120],"multiple":[121,206],"correlating":[124],"models":[125,151],"particular":[128],"domain":[129],"analysis.EMT":[132],"updated":[135],"new":[137,202],"correlation":[138],"functions":[139],"allowing":[140],"analyst":[142],"integrate":[144],"number":[146],"EMT's":[148],"user":[149],"behavior":[150],"available":[152],"core":[155],"technology.":[156],"We":[157,178,199],"present":[158],"results":[159,191],"combining":[161],"classifier":[162],"outputs":[163],"improving":[165],"both":[166],"accuracy":[167,227],"reducing":[169],"problem":[174],"detection.":[177],"apply":[179],"these":[180,197],"methods":[181,195],"large":[185],"set":[188],"show":[190,211],"different":[193],"combination":[194],"corpora.":[198],"introduce":[200],"method":[203,219],"compare":[205],"combined":[208],"classifiers,":[209],"how":[212],"differs":[214],"from":[215],"past":[216],"work.":[217],"analyzes":[220],"relative":[222],"gain":[223],"maximum":[225],"possible":[226],"that":[228],"achieved":[231],"certain":[233],"combinations":[234],"classifiers":[236],"automatically":[238],"choose":[239],"best":[241],"combination.":[242]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}