{"id":"https://openalex.org/W2035488614","doi":"https://doi.org/10.1145/1571941.1572045","title":"Spam filter evaluation with imprecise ground truth","display_name":"Spam filter evaluation with imprecise ground truth","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2035488614","doi":"https://doi.org/10.1145/1571941.1572045","mag":"2035488614"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1572045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","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/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, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","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 Live Labs, Redmond, WA, USA","Microsoft Live Labs, Redmond, WA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Live Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Live Labs, Redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"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":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"604","last_page":"611"},"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":0.9993000030517578,"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":0.9980000257492065,"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":0.7559115886688232},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.738142192363739},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.7104296088218689},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7091993093490601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5171422362327576},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4678680896759033},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29131370782852173},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17444434762001038}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559115886688232},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.738142192363739},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.7104296088218689},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7091993093490601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5171422362327576},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4678680896759033},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29131370782852173},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17444434762001038}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1571941.1572045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.4066","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.4066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://plg.uwaterloo.ca/~gvcormac/cormacksigir09-spam.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W15182600","https://openalex.org/W114599062","https://openalex.org/W171854839","https://openalex.org/W176125184","https://openalex.org/W342038080","https://openalex.org/W1532137412","https://openalex.org/W1605925311","https://openalex.org/W1666146316","https://openalex.org/W1666942233","https://openalex.org/W2041597619","https://openalex.org/W2058737869","https://openalex.org/W2066546027","https://openalex.org/W2092926517","https://openalex.org/W2101919228","https://openalex.org/W2104290684","https://openalex.org/W2118020653","https://openalex.org/W2140821974","https://openalex.org/W2147891303","https://openalex.org/W2170892895","https://openalex.org/W2736182440","https://openalex.org/W2742538188","https://openalex.org/W2916045930","https://openalex.org/W2917688635","https://openalex.org/W3100570787"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W3107474891","https://openalex.org/W2012410061","https://openalex.org/W2130151498","https://openalex.org/W1982685118","https://openalex.org/W2904499449","https://openalex.org/W2952663681","https://openalex.org/W82897008","https://openalex.org/W3099113392","https://openalex.org/W2103567226"],"abstract_inverted_index":{"When":[0],"trained":[1,48],"and":[2,98,115],"evaluated":[3],"on":[4,125],"accurately":[5],"labeled":[6],"datasets,":[7],"online":[8],"email":[9],"spam":[10,72],"filters":[11,44,47],"are":[12,76],"remarkably":[13],"effective,":[14],"achieving":[15],"error":[16,39,93,104,135],"rates":[17,40],"an":[18],"order":[19],"of":[20,53,90,110,122,132],"magnitude":[21],"better":[22],"than":[23,41],"classifiers":[24],"in":[25,70],"similar":[26],"applications.":[27],"But":[28],"labels":[29,62,75],"acquired":[30],"from":[31],"user":[32],"feedback":[33],"or":[34],"third-party":[35],"adjudication":[36],"exhibit":[37],"higher":[38],"the":[42,50,91,102,120],"best":[43],"--":[45,63,66],"even":[46],"using":[49],"same":[51],"source":[52],"labels.":[54],"It":[55],"is":[56],"appropriate":[57],"to":[58,84],"use":[59],"naturally":[60],"occuring":[61],"including":[64],"errors":[65,124],"as":[67,81],"training":[68],"data":[69],"evaluating":[71],"filters.":[73],"Erroneous":[74],"problematic,":[77],"however,":[78],"when":[79],"used":[80],"ground":[82],"truth":[83],"measure":[85],"filter":[86,134],"effectiveness.":[87],"Any":[88],"measurement":[89],"filter's":[92],"rate":[94],"will":[95],"be":[96],"augmented":[97],"perhaps":[99],"masked":[100],"by":[101],"label":[103],"rate.":[105],"Using":[106],"two":[107],"natural":[108],"sources":[109],"labels,":[111],"we":[112],"demonstrate":[113],"automatic":[114],"semi-automatic":[116],"methods":[117],"that":[118],"reduce":[119],"influence":[121],"labeling":[123],"evaluation,":[126],"yielding":[127],"substantially":[128],"more":[129],"precise":[130],"measurements":[131],"true":[133],"rates.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"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":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}