{"id":"https://openalex.org/W5470710","doi":null,"title":"Fast Uncertainty Sampling for Labeling Large E-mail Corpora.","display_name":"Fast Uncertainty Sampling for Labeling Large E-mail Corpora.","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W5470710","mag":"5470710"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.4250","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.4250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ceas.cc/2006/20.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5109910315","display_name":"Richard B. Segal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Segal","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045414075","display_name":"Ted Markowitz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ted Markowitz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038017609","display_name":"William R. Arnold","orcid":"https://orcid.org/0000-0003-2231-9496","observed_orcids":["https://orcid.org/0000-0003-2231-9496"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William R. Arnold","raw_affiliation_strings":["IBM, ,"],"raw_orcid":"https://orcid.org/0000-0003-2231-9496","affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.933,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96113036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9897000193595886,"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":0.9897000193595886,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.008200000040233135,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0006000000284984708,"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/uncertainty-sampling","display_name":"uncertainty sampling","score":0.8730000257492065},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.7879999876022339},{"id":"https://openalex.org/keywords/spam-filtering","display_name":"spam filtering","score":0.7639999985694885},{"id":"https://openalex.org/keywords/anti-spam","display_name":"anti-spam","score":0.8330000042915344},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.578000009059906},{"id":"https://openalex.org/keywords/binary-classification","display_name":"binary classification","score":0.4729999899864197},{"id":"https://openalex.org/keywords/model-updating","display_name":"model updating","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262192606925964},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.70535808801651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5961296558380127},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5594761967658997},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.527982771396637},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48335736989974976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46520739793777466},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4335181713104248},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.20294317603111267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09400081634521484},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.4250","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.4250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ceas.cc/2006/20.pdf","raw_type":"text"},{"id":"mag:5470710","doi":null,"is_oa":false,"landing_page_url":"http://csis.pace.edu/~ctappert/srd2007/c3.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418051","display_name":"Conference on Email and Anti-Spam","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Email and Anti-Spam","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W114599062","https://openalex.org/W1484084878","https://openalex.org/W1513874326","https://openalex.org/W1756896031","https://openalex.org/W2018810220","https://openalex.org/W2080021732","https://openalex.org/W2085989833","https://openalex.org/W2091110562","https://openalex.org/W2122520221","https://openalex.org/W2149684865","https://openalex.org/W2426031434","https://openalex.org/W2949071206","https://openalex.org/W3112138688"],"related_works":["https://openalex.org/W7098892140","https://openalex.org/W2351335636","https://openalex.org/W2344129941","https://openalex.org/W2125667824","https://openalex.org/W2185861556","https://openalex.org/W31602239","https://openalex.org/W2035488614","https://openalex.org/W1601302864","https://openalex.org/W3171396409","https://openalex.org/W1988046929"],"abstract_inverted_index":{"One":[0],"of":[1,19,27,43,60,68,79,102,118,122,132,244,266,269,286,293],"the":[2,16,44,56,77,108,116,130,150,176,181,233,242,263],"biggest":[3],"challenges":[4],"in":[5,76,91,97,112],"building":[6,243],"effective":[7],"anti-spam":[8,62,257],"solutions":[9],"is":[10,88,137,170,198],"designing":[11],"systems":[12],"to":[13,23,148,154,165,219,222,231],"defend":[14],"against":[15],"everevolving":[17],"bag":[18],"tricks":[20],"spammers":[21],"use":[22],"defeat":[24],"them.":[25],"Because":[26],"this,":[28],"spam":[29,45,126],"filters":[30],"that":[31],"work":[32,37],"well":[33,38],"today":[34],"may":[35],"not":[36,89],"tomorrow.":[39],"The":[40,86,211],"adversarial":[41],"nature":[42],"problem":[46],"makes":[47,228],"large,":[48,81],"up-to-date,":[49],"and":[50,58,111,226,248],"diverse":[51],"e-mail":[52,252,270],"corpora":[53,253],"critical":[54],"for":[55,254,290],"development":[57],"evaluation":[59],"new":[61,191,256],"filtering":[63],"technologies.":[64],"Gathering":[65],"large":[66,156,267],"collections":[67],"messages":[69,124],"can":[70,279],"actually":[71],"be":[72,166,220,280],"quite":[73],"easy,":[74],"especially":[75],"context":[78],"a":[80,99,138,145,190,283,291],"corporate":[82],"or":[83,120,127],"ISP":[84],"environment.":[85],"challenge":[87],"necessarily":[90],"collecting":[92,98],"enough":[93],"mail,":[94],"however,":[95],"but":[96,205],"representative":[100],"distribution":[101],"mail":[103],"types":[104],"as":[105,125,200,202,272],"seen":[106],"\u201cin":[107],"wild":[109],"\u201d":[110],"then":[113],"accurately":[114],"labeling":[115,223,265],"hundreds":[117],"thousands":[119],"millions":[121],"accumulated":[123],"non-spam.":[128],"In":[129],"field":[131],"machine":[133],"learning":[134,186],"Uncertainty":[135,160,194,203,217,239,274,277],"Sampling":[136,161,195,218,240,278],"well-known":[139],"Active":[140],"Learning":[141],"algorithm":[142],"which":[143,197],"uses":[144],"collaborative":[146],"model":[147,235],"minimize":[149],"human":[151],"effort":[152],"required":[153],"label":[155],"datasets.":[157],"While":[158,259],"conventional":[159],"has":[162,206],"been":[163],"shown":[164],"very":[167,173],"effective,":[168],"it":[169,229],"also":[171,227],"computationally":[172],"expensive":[174],"since":[175],"learner":[177],"must":[178],"reclassify":[179],"all":[180],"unlabeled":[182],"instances":[183],"during":[184],"each":[185],"iteration.":[187],"We":[188],"propose":[189],"algorithm,":[192],"Approximate":[193,216,238,276],"(AUS),":[196],"nearly":[199],"efficacious":[201],"Sampling,":[204,275],"substantially":[207],"lower":[208],"computational":[209,213],"complexity.":[210],"reduced":[212],"cost":[214],"allows":[215],"applied":[221],"larger":[224],"datasets":[225],"possible":[230],"update":[232],"learned":[234],"more":[236,246,249],"frequently.":[237],"encourages":[241],"larger,":[245],"topical,":[247],"realistic":[250],"example":[251],"evaluating":[255],"filters.":[258],"we":[260],"focus":[261],"on":[262],"binary":[264],"volumes":[268],"messages,":[271],"with":[273,282],"used":[281],"wide":[284],"range":[285],"underlying":[287],"classification":[288],"algorithms":[289],"variety":[292],"categorization":[294],"tasks.":[295],"1.":[296]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-03T13:16:28.481748","created_date":"2016-06-24T00:00:00"}