{"id":"https://openalex.org/W1603063705","doi":null,"title":"Ending Spam: Bayesian Content Filtering and the Art of Statistical Language Classification","display_name":"Ending Spam: Bayesian Content Filtering and the Art of Statistical Language Classification","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1603063705","mag":"1603063705"},"language":"en","primary_location":{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-016474497","doi":null,"is_oa":false,"landing_page_url":"http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=016474497&sequence=000013&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5013191875","display_name":"Jonathan Zdziarski","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jonathan Zdziarski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5013191875"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0655,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.96949506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.0,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0,"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/spam-filtering","display_name":"spam filtering","score":0.8989999890327454},{"id":"https://openalex.org/keywords/spam","display_name":"spam","score":0.5809999704360962},{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.7580000162124634},{"id":"https://openalex.org/keywords/decoding","display_name":"decoding","score":0.38999998569488525},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.7910000085830688},{"id":"https://openalex.org/keywords/feature-reduction","display_name":"feature reduction","score":0.722000002861023},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"collaborative filtering","score":0.7239999771118164}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7617822289466858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158604860305786},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.6485185027122498},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.5963564515113831},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.551746129989624},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.4747738540172577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4721032679080963},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.3968549966812134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3543741703033447},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3388150930404663},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2503911852836609},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.1645805835723877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-016474497","doi":null,"is_oa":false,"landing_page_url":"http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=016474497&sequence=000013&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-028554007","doi":null,"is_oa":false,"landing_page_url":"http://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=440039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"software, multimedia"},{"id":"pmh:oai:cds.cern.ch:1511589","doi":null,"is_oa":false,"landing_page_url":"http://cds.cern.ch/record/1511589","pdf_url":null,"source":{"id":"https://openalex.org/S4306402195","display_name":"CERN Document Server (European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:1603063705","doi":null,"is_oa":false,"landing_page_url":"https://openlibrary.org/books/OL8871407M/Ending_Spam","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W70610779","https://openalex.org/W274899702","https://openalex.org/W7096461897","https://openalex.org/W73527130","https://openalex.org/W2167529272","https://openalex.org/W2368090696","https://openalex.org/W2187526005","https://openalex.org/W2131610505","https://openalex.org/W2033485922","https://openalex.org/W7216720063"],"abstract_inverted_index":{"Join":[0],"author":[1],"John":[2],"Zdziarski":[3,105],"for":[4,238],"a":[5,70,130,133,137,141,239],"look":[6],"inside":[7],"the":[8,74,96,111,125,155,171],"brilliant":[9],"minds":[10],"that":[11],"have":[12,69],"conceived":[13],"clever":[14],"new":[15,134],"ways":[16],"to":[17,40,58,102,159,181,194],"fight":[18],"spam":[19,38,47,62,80,113,135,151],"in":[20,120,245],"all":[21],"its":[22],"nefarious":[23],"forms.":[24],"This":[25],"landmark":[26],"title":[27],"describes,":[28],"in-depth,":[29],"how":[30,46,51,150],"statistical":[31],"filtering":[32,48],"is":[33],"being":[34],"used":[35,77],"by":[36,78],"next-generation":[37],"filters":[39,81,114,152],"identify":[41],"and":[42,50,54,92,95,115,154],"filter":[43],"unwanted":[44],"messages,":[45],"works":[49],"language":[52],"classification":[53],"machine":[55],"learning":[56],"combine":[57],"produce":[59],"remarkably":[60],"accurate":[61],"filters.":[63],"After":[64],"reading":[65],"Ending":[66,162],"Spam,":[67],"you'll":[68],"complete":[71],"understanding":[72],"of":[73,98,108,110,124,170,188,210,224,232,252,283],"mathematical":[75],"approaches":[76],"today's":[79],"as":[82,84,166],"well":[83],"decoding,":[85],"tokenization,":[86],"various":[87],"algorithms":[88],"(including":[89],"Bayesian":[90],"analysis":[91,169],"Markovian":[93,268],"discrimination)":[94],"benefits":[97],"using":[99],"open-source":[100],"solutions":[101],"end":[103],"spam.":[104],"interviewed":[106],"creators":[107],"many":[109],"best":[112],"has":[116],"included":[117],"their":[118],"insights":[119],"this":[121],"revealing":[122],"examination":[123],"anti-spam":[126],"crusade.":[127],"If":[128],"you're":[129],"programmer":[131],"designing":[132],"filter,":[136],"network":[138],"admin":[139],"implementing":[140],"spam-filtering":[142],"solution,":[143],"or":[144],"just":[145],"someone":[146],"who's":[147],"curious":[148],"about":[149],"work":[153],"tactics":[156],"spammers":[157],"use":[158],"evade":[160],"them,":[161],"Spam":[163,182,189,196,225],"will":[164],"serve":[165],"an":[167],"informative":[168],"war":[172],"against":[173],"spammers.":[174],"TOC":[175],"Introduction":[176,180],"PART":[177,207,248],"I:":[178],"An":[179],"Filtering":[183,205,212,254,284],"Chapter":[184,190,197,202,213,218,226,234,242,255,259,265,270,276],"1:":[185],"The":[186,221,228],"History":[187],"2:":[191],"Historical":[192],"Approaches":[193],"Fighting":[195],"3:":[198],"Language":[199],"Classification":[200],"Concepts":[201,251],"4:":[203],"Statistical":[204,211,253],"Fundamentals":[206,209],"II:":[208],"5:":[214],"Decoding:":[215],"Uncombobulating":[216],"Messages":[217],"6:":[219],"Tokenization:":[220],"Building":[222],"Blocks":[223],"7:":[227],"Low-Down":[229],"Dirty":[230],"Tricks":[231],"Spammers":[233],"8:":[235],"Data":[236],"Storage":[237],"Zillion":[240],"Records":[241],"9:":[243],"Scaling":[244],"Large":[246],"Environments":[247],"III:":[249],"Advanced":[250,263],"10:":[256],"Testing":[257],"Theory":[258],"11:":[260],"Concept":[261],"Identification:":[262],"Tokenization":[264],"12:":[266],"Fifth-Order":[267],"Discrimination":[269],"13:":[271],"Intelligent":[272],"Feature":[273],"Set":[274],"Reduction":[275],"14:":[277],"Collaborative":[278],"Algorithms":[279],"Appendix:":[280],"Shining":[281],"Examples":[282],"Index":[285]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":15}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}