{"id":"https://openalex.org/W2058250637","doi":"https://doi.org/10.1145/1835449.1835598","title":"Semi-supervised spam filtering using aggressive consistency learning","display_name":"Semi-supervised spam filtering using aggressive consistency learning","publication_year":2010,"publication_date":"2010-07-19","ids":{"openalex":"https://openalex.org/W2058250637","doi":"https://doi.org/10.1145/1835449.1835598","mag":"2058250637"},"language":"en","primary_location":{"id":"doi:10.1145/1835449.1835598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5049510396","display_name":"Mona Mojdeh","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":"Mona Mojdeh","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"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, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049510396"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":1.3874,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88091596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"751","last_page":"752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/consistency","display_name":"Consistency (knowledge bases)","score":0.78920578956604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7867528200149536},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6192253232002258},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5270930528640747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49858808517456055},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.49830031394958496},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.49340739846229553},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40460142493247986},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3437703847885132},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34171444177627563},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1016213595867157},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0682874321937561}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.78920578956604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867528200149536},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6192253232002258},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5270930528640747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49858808517456055},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.49830031394958496},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.49340739846229553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40460142493247986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3437703847885132},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34171444177627563},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1016213595867157},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0682874321937561}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1835449.1835598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1963709204","https://openalex.org/W2130196635","https://openalex.org/W2148541040","https://openalex.org/W2154455818","https://openalex.org/W2613433911","https://openalex.org/W6682494755"],"related_works":["https://openalex.org/W1603736412","https://openalex.org/W4304185162","https://openalex.org/W2061685118","https://openalex.org/W3006282800","https://openalex.org/W2462100143","https://openalex.org/W1770503332","https://openalex.org/W3125207769","https://openalex.org/W2577825108","https://openalex.org/W2949684406","https://openalex.org/W2140728006"],"abstract_inverted_index":{"A":[0],"graph":[1],"based":[2,9],"semi-supervised":[3],"method":[4,31],"for":[5],"email":[6,78],"spam":[7,33,50,97],"filtering,":[8],"on":[10,72],"the":[11,45,67,85],"local":[12],"and":[13,75,98],"global":[14],"consistency":[15],"method,":[16],"yields":[17],"low":[18],"error":[19],"rates":[20],"with":[21,35,84],"very":[22,38],"few":[23,39,90],"labeled":[24,40,56,94],"examples.":[25],"The":[26],"motivating":[27],"application":[28],"of":[29,48,55,69],"this":[30],"is":[32],"filters":[34],"access":[36],"to":[37],"message.":[41],"For":[42],"example,":[43],"during":[44],"initial":[46],"deployment":[47],"a":[49,53],"filter,":[51],"only":[52],"handful":[54],"examples":[57,62],"are":[58,63],"available":[59],"but":[60],"unlabeled":[61],"plentiful.":[64],"We":[65],"demonstrate":[66],"performance":[68],"our":[70],"approach":[71],"TREC":[73],"2007":[74],"CEAS":[76],"2008":[77],"corpora.":[79],"Our":[80],"results":[81],"compare":[82],"favorably":[83],"best-known":[86],"methods,":[87],"using":[88],"as":[89,91],"just":[92],"two":[93],"examples:":[95],"one":[96,99],"non-spam.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}