{"id":"https://openalex.org/W2066546027","doi":"https://doi.org/10.1145/1148170.1148195","title":"On-line spam filter fusion","display_name":"On-line spam filter fusion","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2066546027","doi":"https://doi.org/10.1145/1148170.1148195","mag":"2066546027"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5016776505","display_name":"Thomas R. Lynam","orcid":null},"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":true,"raw_author_name":"Thomas R. Lynam","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada","University of Waterloo, Waterloo, Ontario, CANADA"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, CANADA","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","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, Ontario, Canada","University of Waterloo, Waterloo, Ontario, CANADA"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, CANADA","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032416534","display_name":"David R. Cheriton","orcid":null},"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":"David R. Cheriton","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada","University of Waterloo, Waterloo, Ontario, CANADA"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, CANADA","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016776505"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":19.7002,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.99080905,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9973999857902527,"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/filter","display_name":"Filter (signal processing)","score":0.7129786610603333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7010445594787598},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.6619354486465454},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.5803657174110413},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5148395895957947},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49950098991394043},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.48930618166923523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4596947729587555},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4368099570274353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42891934514045715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2860461473464966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21283629536628723},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0848422646522522}],"concepts":[{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.7129786610603333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010445594787598},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.6619354486465454},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.5803657174110413},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5148395895957947},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49950098991394043},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.48930618166923523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4596947729587555},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4368099570274353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42891934514045715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2860461473464966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21283629536628723},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0848422646522522},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1148170.1148195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W10423024","https://openalex.org/W28412257","https://openalex.org/W155555924","https://openalex.org/W1521843029","https://openalex.org/W1534477342","https://openalex.org/W1574862351","https://openalex.org/W2002157036","https://openalex.org/W2020237802","https://openalex.org/W2023294425","https://openalex.org/W2023991263","https://openalex.org/W2035344247","https://openalex.org/W2060216474","https://openalex.org/W2078396654","https://openalex.org/W2084044465","https://openalex.org/W2084457609","https://openalex.org/W2092276439","https://openalex.org/W2110891465","https://openalex.org/W2111310810","https://openalex.org/W2118020653","https://openalex.org/W2139242327","https://openalex.org/W2146081744","https://openalex.org/W2150871663","https://openalex.org/W2158275940","https://openalex.org/W2171622762","https://openalex.org/W2318960778","https://openalex.org/W2792952625","https://openalex.org/W4230856572"],"related_works":["https://openalex.org/W2035329725","https://openalex.org/W4376641153","https://openalex.org/W2070875936","https://openalex.org/W4250391473","https://openalex.org/W3045075405","https://openalex.org/W4302292679","https://openalex.org/W4241625287","https://openalex.org/W2050788868","https://openalex.org/W4295885776","https://openalex.org/W2027634686"],"abstract_inverted_index":{"We":[0],"show":[1,151],"that":[2,152],"a":[3,66,90,112,158,175],"set":[4],"of":[5,23,29,51,68,162],"independently":[6],"developed":[7],"spam":[8,31],"filters":[9,32,87,109,164],"may":[10],"be":[11],"combined":[12,41,55],"in":[13],"simple":[14],"ways":[15],"to":[16,45,119,129,156],"provide":[17,130],"substantially":[18],"better":[19,114,147],"filtering":[20],"than":[21,65],"any":[22],"the":[24,35,47,52,60,72,80,85,103,107,140,146,163,170],"individual":[25,86,108,172],"filters.":[26,53],"The":[27,54,75,125],"results":[28,56],"fifty-three":[30],"evaluated":[33,58],"at":[34],"TREC":[36,61],"2005":[37],"Spam":[38],"Track":[39],"were":[40,57],"post-hoc":[42],"so":[43],"as":[44],"simulate":[46],"parallel":[48],"on-line":[49],"operation":[50],"using":[59],"methodology,":[62],"yielding":[63],"more":[64],"factor":[67],"two":[69],"improvement":[70],"over":[71],"best":[73,171],"filter.":[74],"simplest":[76],"method":[77,96],"--":[78,88,97,110],"averaging":[79,98],"binary":[81],"classifications":[82],"returned":[83,105],"by":[84,106,174],"yields":[89,111,145],"remarkably":[91],"good":[92],"result.":[93,148],"A":[94],"new":[95],"log-odds":[99],"estimates":[100],"based":[101],"on":[102],"scores":[104],"somewhat":[113],"result,":[115],"and":[116,121],"provides":[117],"input":[118],"SVM-":[120],"logistic-regression-based":[122],"stacking":[123,126,141],"methods.":[124],"methods":[127],"appear":[128],"further":[131],"improvement,":[132],"but":[133],"only":[134],"for":[135],"very":[136],"large":[137],"corpora.":[138],"Of":[139],"methods,":[142],"logistic":[143],"regression":[144],"Finally,":[149],"we":[150],"it":[153],"is":[154],"possible":[155],"select":[157],"priori":[159],"small":[160],"subsets":[161],"that,":[165],"when":[166],"combined,":[167],"still":[168],"outperform":[169],"filter":[173],"substantial":[176],"margin.":[177]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}