{"id":"https://openalex.org/W2099937822","doi":"https://doi.org/10.1145/1935826.1935929","title":"Enhanced email spam filtering through combining similarity graphs","display_name":"Enhanced email spam filtering through combining similarity graphs","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2099937822","doi":"https://doi.org/10.1145/1935826.1935929","mag":"2099937822"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5061449196","display_name":"Anirban Dasgupta","orcid":"https://orcid.org/0000-0002-8494-3692"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anirban Dasgupta","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086993894","display_name":"Maxim Gurevich","orcid":"https://orcid.org/0000-0003-4693-0556"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxim Gurevich","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089487172","display_name":"Kunal Punera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Punera","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061449196"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":7.6384,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.96911671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"785","last_page":"794"},"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9975000023841858,"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":0.989799976348877,"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/spamming","display_name":"Spamming","score":0.9816842675209045},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.8719236850738525},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.7518283128738403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7157153487205505},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6874783635139465},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5538687109947205},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5247849822044373},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4673108756542206},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4390731453895569},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4306570291519165},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.417254775762558},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.3928653597831726},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.365028440952301},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3304878771305084},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.2683882713317871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2516114413738251},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.23422598838806152},{"id":"https://openalex.org/keywords/web-2.0","display_name":"Web 2.0","score":0.11099541187286377},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.10844269394874573},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07972288131713867}],"concepts":[{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.9816842675209045},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.8719236850738525},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.7518283128738403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157153487205505},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6874783635139465},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5538687109947205},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5247849822044373},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4673108756542206},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4390731453895569},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4306570291519165},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.417254775762558},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3928653597831726},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.365028440952301},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3304878771305084},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2683882713317871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2516114413738251},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.23422598838806152},{"id":"https://openalex.org/C136699151","wikidata":"https://www.wikidata.org/wiki/Q131164","display_name":"Web 2.0","level":3,"score":0.11099541187286377},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.10844269394874573},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07972288131713867},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1935826.1935929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.4040","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.4040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ideal.ece.utexas.edu/~kunal/papers/wsdm2011-mailrecomm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W37118932","https://openalex.org/W176125184","https://openalex.org/W1513158862","https://openalex.org/W1560502112","https://openalex.org/W1648885110","https://openalex.org/W1956666414","https://openalex.org/W1990295648","https://openalex.org/W2040717637","https://openalex.org/W2041597619","https://openalex.org/W2054141820","https://openalex.org/W2054553473","https://openalex.org/W2060820597","https://openalex.org/W2070771761","https://openalex.org/W2070996757","https://openalex.org/W2090641502","https://openalex.org/W2091692346","https://openalex.org/W2104290684","https://openalex.org/W2115394986","https://openalex.org/W2119384858","https://openalex.org/W2131906261","https://openalex.org/W2137728971","https://openalex.org/W2293768274","https://openalex.org/W2294919332","https://openalex.org/W2610985164","https://openalex.org/W2990138404"],"related_works":["https://openalex.org/W2091208042","https://openalex.org/W2080521416","https://openalex.org/W2006090454","https://openalex.org/W2031843194","https://openalex.org/W3098355271","https://openalex.org/W2920666515","https://openalex.org/W2738482239","https://openalex.org/W2246912952","https://openalex.org/W2552201931","https://openalex.org/W1551975479"],"abstract_inverted_index":{"Over":[0],"the":[1,47,85,90],"last":[2],"decade":[3],"Email":[4],"Spam":[5],"has":[6,20],"evolved":[7],"from":[8],"being":[9,16],"just":[10],"an":[11],"irritant":[12],"to":[13,15,27,72],"users":[14],"truly":[17],"dangerous.":[18],"This":[19],"led":[21],"web-mail":[22],"providers":[23],"and":[24,75,84,87],"academic":[25],"researchers":[26],"dedicate":[28],"considerable":[29],"resources":[30],"towards":[31],"tackling":[32],"this":[33],"problem":[34,50],"[9,":[35],"21,":[36],"22,":[37],"24,":[38],"26].":[39],"However,":[40],"we":[41],"argue":[42],"that":[43],"some":[44],"aspects":[45],"of":[46,89,101],"spam":[48,70],"filtering":[49],"are":[51,61],"not":[52],"handled":[53],"appropriately":[54],"in":[55],"existing":[56],"work.":[57],"Principal":[58],"among":[59],"these":[60],"adversarial":[62],"spammer":[63],"efforts":[64],"--":[65,83],"spammers":[66],"routinely":[67],"tune":[68],"their":[69],"emails":[71],"bypass":[73],"spam-filters,":[74],"contaminate":[76],"ground":[77],"truth":[78],"via":[79],"fake":[80],"HAM/SPAM":[81],"votes":[82],"scale":[86],"sparsity":[88],"problem,":[91],"which":[92],"essentially":[93],"precludes":[94],"learning":[95],"with":[96],"a":[97],"very":[98],"large":[99],"set":[100],"parameters.":[102]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"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":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
