{"id":"https://openalex.org/W1997665666","doi":"https://doi.org/10.1145/1774088.1774481","title":"Filtering spams using the minimum description length principle","display_name":"Filtering spams using the minimum description length principle","publication_year":2010,"publication_date":"2010-03-22","ids":{"openalex":"https://openalex.org/W1997665666","doi":"https://doi.org/10.1145/1774088.1774481","mag":"1997665666"},"language":"en","primary_location":{"id":"doi:10.1145/1774088.1774481","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","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/A5070893483","display_name":"Tiago A. Almeida","orcid":"https://orcid.org/0000-0001-6943-8033"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Tiago A. Almeida","raw_affiliation_strings":["University of Campinas, Campinas, SP, Brazil","University of Campinas, Campinas (SP), Brazil"],"affiliations":[{"raw_affiliation_string":"University of Campinas, Campinas, SP, Brazil","institution_ids":["https://openalex.org/I181391015"]},{"raw_affiliation_string":"University of Campinas, Campinas (SP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068549079","display_name":"Akebo Yamakami","orcid":"https://orcid.org/0000-0003-3537-4638"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Akebo Yamakami","raw_affiliation_strings":["University of Campinas, Campinas, SP, Brazil","University of Campinas, Campinas (SP), Brazil"],"affiliations":[{"raw_affiliation_string":"University of Campinas, Campinas, SP, Brazil","institution_ids":["https://openalex.org/I181391015"]},{"raw_affiliation_string":"University of Campinas, Campinas (SP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089568142","display_name":"Jurandy Almeida","orcid":"https://orcid.org/0000-0002-4998-6996"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jurandy Almeida","raw_affiliation_strings":["University of Campinas, Campinas, SP, Brazil","University of Campinas, Campinas (SP), Brazil"],"affiliations":[{"raw_affiliation_string":"University of Campinas, Campinas, SP, Brazil","institution_ids":["https://openalex.org/I181391015"]},{"raw_affiliation_string":"University of Campinas, Campinas (SP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070893483"],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":11.0992,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.98113542,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1854","last_page":"1858"},"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":0.9987999796867371,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9955999851226807,"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":0.7992151379585266},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.7539365291595459},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6250588893890381},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6167832016944885},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5819827914237976},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4855737090110779},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.483333557844162},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.47998449206352234},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.45808497071266174},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.4480776786804199},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.43006670475006104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4203207492828369},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4109305739402771},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39692848920822144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3499715328216553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2544049620628357},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1798156201839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992151379585266},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.7539365291595459},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6250588893890381},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6167832016944885},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5819827914237976},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4855737090110779},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.483333557844162},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.47998449206352234},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.45808497071266174},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.4480776786804199},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.43006670475006104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4203207492828369},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4109305739402771},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39692848920822144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3499715328216553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2544049620628357},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1798156201839447},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1774088.1774481","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W39304953","https://openalex.org/W327991062","https://openalex.org/W1482320265","https://openalex.org/W1504008138","https://openalex.org/W1585280831","https://openalex.org/W2033485922","https://openalex.org/W2040424159","https://openalex.org/W2054658115","https://openalex.org/W2058737869","https://openalex.org/W2061989622","https://openalex.org/W2096152098","https://openalex.org/W2102098892","https://openalex.org/W2104290684","https://openalex.org/W2108313281","https://openalex.org/W2109553965","https://openalex.org/W2131438151","https://openalex.org/W2160536005","https://openalex.org/W2166490929","https://openalex.org/W2169384781","https://openalex.org/W4253654031","https://openalex.org/W4297970707","https://openalex.org/W6630221274"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"Spam":[0,14],"has":[1],"become":[2],"an":[3,32,72,105],"increasingly":[4],"important":[5],"problem":[6,19],"with":[7],"a":[8,17,46,92,99],"big":[9],"economic":[10],"impact":[11],"in":[12,20,95],"society.":[13],"filtering":[15,51],"poses":[16],"special":[18],"text":[21],"categorization,":[22],"of":[23,83],"which":[24,35],"the":[25,54,75,81,84,116,123],"defining":[26],"characteristic":[27],"is":[28,62],"that":[29,119],"filters":[30],"face":[31],"active":[33],"adversary,":[34],"constantly":[36],"attempts":[37],"to":[38,49,64,79,97],"evade":[39],"filtering.":[40],"In":[41,87],"this":[42,88],"paper,":[43],"we":[44,70,90,103],"present":[45,91],"novel":[47],"approach":[48,121],"spam":[50,125],"based":[52],"on":[53],"minimum":[55],"description":[56],"length":[57],"principle.":[58],"The":[59],"proposed":[60],"model":[61],"fast":[63],"construct":[65],"and":[66,112],"incrementally":[67],"updateable.":[68],"Additionally,":[69],"offer":[71],"analysis":[73],"concerning":[74],"measurements":[76],"usually":[77],"employed":[78],"evaluate":[80],"quality":[82],"anti-spam":[85],"classifiers.":[86],"sense,":[89],"new":[93],"measure":[94],"order":[96],"provide":[98],"fairer":[100],"comparison.":[101],"Furthermore,":[102],"conducted":[104],"empirical":[106],"experiment":[107],"using":[108],"six":[109],"well-known,":[110],"large":[111],"public":[113],"databases.":[114],"Finally,":[115],"results":[117],"indicate":[118],"our":[120],"outperforms":[122],"state-of-the-art":[124],"filters.":[126]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}