{"id":"https://openalex.org/W1963709204","doi":"https://doi.org/10.1145/1390334.1390482","title":"Semi-supervised spam filtering","display_name":"Semi-supervised spam filtering","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W1963709204","doi":"https://doi.org/10.1145/1390334.1390482","mag":"1963709204"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/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":5.0756,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95001744,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"745","last_page":"746"},"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":0.9988999962806702,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.6894353032112122},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.5100947022438049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5071649551391602},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.4412010610103607},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.4236075282096863},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15844818949699402},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.11992624402046204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894353032112122},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.5100947022438049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5071649551391602},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.4412010610103607},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.4236075282096863},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15844818949699402},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.11992624402046204}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390334.1390482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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":7,"referenced_works":["https://openalex.org/W19132006","https://openalex.org/W176125184","https://openalex.org/W1574862351","https://openalex.org/W2101919228","https://openalex.org/W2104290684","https://openalex.org/W2170580685","https://openalex.org/W2916045930"],"related_works":["https://openalex.org/W2018000323","https://openalex.org/W2095720311","https://openalex.org/W2403960249","https://openalex.org/W2898345088","https://openalex.org/W2080521416","https://openalex.org/W1937320931","https://openalex.org/W2075252441","https://openalex.org/W1502194589","https://openalex.org/W1965586806","https://openalex.org/W4293384513"],"abstract_inverted_index":{"The":[0],"results":[1,37],"of":[2,21],"the":[3,19,41,51,72,80,92],"2006":[4],"ECML/PKDD":[5,81],"Discovery":[6],"Challenge":[7],"suggest":[8],"that":[9,88],"semi-supervised":[10],"learning":[11,70],"methods":[12,54],"work":[13],"well":[14],"for":[15,91],"spam":[16],"filtering":[17],"when":[18],"source":[20],"available":[22],"labeled":[23,73],"examples":[24],"differs":[25],"from":[26,40],"those":[27,66],"to":[28,34,65],"be":[29],"classified.":[30],"We":[31,76],"have":[32,49],"attempted":[33],"reproduce":[35],"these":[36],"using":[38,68],"data":[39,74,84],"2005":[42],"and":[43,48,57,82,86],"2007":[44],"TREC":[45,83],"Spam":[46],"Track,":[47],"found":[50],"opposite":[52,93],"effect:":[53],"like":[55],"self-training":[56],"transductive":[58],"support":[59],"vector":[60],"machines":[61],"yield":[62],"inferior":[63],"classifiers":[64],"constructed":[67],"supervised":[69],"on":[71],"alone.":[75],"investigate":[77],"differences":[78],"between":[79],"sets":[85],"methodologies":[87],"may":[89],"account":[90],"results.":[94]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
