{"id":"https://openalex.org/W2059778803","doi":"https://doi.org/10.1145/1774088.1774469","title":"Probabilistic anti-spam filtering with dimensionality reduction","display_name":"Probabilistic anti-spam filtering with dimensionality reduction","publication_year":2010,"publication_date":"2010-03-22","ids":{"openalex":"https://openalex.org/W2059778803","doi":"https://doi.org/10.1145/1774088.1774469","mag":"2059778803"},"language":"en","primary_location":{"id":"doi:10.1145/1774088.1774469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774469","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":10.4056,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.98012702,"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":"1802","last_page":"1806"},"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":0.9998999834060669,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9944000244140625,"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/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.7821290493011475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808212041854858},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.7209056615829468},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6549792289733887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6258330345153809},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6219461560249329},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5633509755134583},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.5074612498283386},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4818952679634094},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4734850823879242},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.46526220440864563},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.43608444929122925},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42823225259780884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4244816303253174},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.41771215200424194},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4176383912563324},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4175460934638977},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.36853376030921936},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.22432667016983032}],"concepts":[{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7821290493011475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808212041854858},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.7209056615829468},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6549792289733887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258330345153809},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6219461560249329},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5633509755134583},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.5074612498283386},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4818952679634094},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4734850823879242},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.46526220440864563},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.43608444929122925},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42823225259780884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4244816303253174},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.41771215200424194},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4176383912563324},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4175460934638977},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.36853376030921936},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.22432667016983032},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1774088.1774469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774469","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":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"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":9,"referenced_works":["https://openalex.org/W39304953","https://openalex.org/W2061989622","https://openalex.org/W2087787226","https://openalex.org/W2107432340","https://openalex.org/W2118020653","https://openalex.org/W2131438151","https://openalex.org/W2160536005","https://openalex.org/W2435251607","https://openalex.org/W4297970707"],"related_works":["https://openalex.org/W2537862391","https://openalex.org/W2417174640","https://openalex.org/W6057950","https://openalex.org/W3152580332","https://openalex.org/W4389581355","https://openalex.org/W4377970780","https://openalex.org/W1824099197","https://openalex.org/W1594281393","https://openalex.org/W4281766958","https://openalex.org/W2891503321"],"abstract_inverted_index":{"One":[0],"of":[1,5,16,42,71,93,107,118,130],"the":[2,9,65,68,72,83,91,100,105,108,116,131],"biggest":[3],"problems":[4],"e-mail":[6],"communication":[7],"is":[8,87],"massive":[10],"spam":[11],"message":[12],"delivery.":[13],"Everyday,":[14],"billion":[15],"unwanted":[17],"messages":[18],"are":[19,32,49],"sent":[20],"by":[21],"spammers":[22],"and":[23,39,45],"this":[24,112],"number":[25],"does":[26],"not":[27],"stop":[28],"growing.":[29],"Helpfully,":[30],"there":[31],"different":[33],"approaches":[34],"able":[35],"to":[36,61],"automatically":[37],"detect":[38],"remove":[40],"most":[41,119],"these":[43],"messages,":[44],"a":[46],"well-known":[47],"ones":[48],"based":[50],"on":[51,99],"Bayesian":[52],"decision":[53],"theory.":[54],"However,":[55],"many":[56],"machine":[57],"learning":[58],"techniques":[59,126],"applied":[60,102],"text":[62],"categorization":[63],"have":[64,79],"same":[66],"difficulty:":[67],"high":[69],"dimensionality":[70,106],"feature":[73,109],"space.":[74,110],"Many":[75],"term":[76,124],"selection":[77,125],"methods":[78,101,121],"been":[80],"proposed":[81],"in":[82],"literature.":[84],"Nevertheless,":[85],"it":[86],"still":[88],"unclear":[89],"how":[90],"performance":[92,117],"naive":[94,133],"Bayes":[95,134],"anti-spam":[96,135],"filters":[97],"depends":[98],"for":[103],"reducing":[104],"In":[111],"paper,":[113],"we":[114],"compare":[115],"popular":[120],"used":[122],"as":[123],"with":[127],"some":[128],"variations":[129],"original":[132],"filter.":[136]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"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"}