{"id":"https://openalex.org/W2085302848","doi":"https://doi.org/10.1145/345508.345569","title":"An experimental comparison of naive Bayesian and keyword-based anti-spam filtering with personal e-mail messages","display_name":"An experimental comparison of naive Bayesian and keyword-based anti-spam filtering with personal e-mail messages","publication_year":2000,"publication_date":"2000-07-01","ids":{"openalex":"https://openalex.org/W2085302848","doi":"https://doi.org/10.1145/345508.345569","mag":"2085302848"},"language":"en","primary_location":{"id":"doi:10.1145/345508.345569","doi":"https://doi.org/10.1145/345508.345569","is_oa":true,"landing_page_url":"https://doi.org/10.1145/345508.345569","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/345508.345569","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/345508.345569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069270736","display_name":"Ion Androutsopoulos","orcid":"https://orcid.org/0009-0000-2969-0509","observed_orcids":["https://orcid.org/0009-0000-2969-0509"]},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ion Androutsopoulos","raw_affiliation_strings":["Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006103845","display_name":"John Koutsias","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"John Koutsias","raw_affiliation_strings":["Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029411863","display_name":"Konstantinos V. Chandrinos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos V. Chandrinos","raw_affiliation_strings":["Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051035784","display_name":"Constantine D. Spyropoulos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Constantine D. Spyropoulos","raw_affiliation_strings":["Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, National Centre for Scientific Research 'Demokritos', 153 10 Ag. Paraskevi, Athens, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9522,"has_fulltext":true,"cited_by_count":480,"citation_normalized_percentile":{"value":0.96360213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"160","last_page":"167"},"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":9.999999747378752e-05,"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":0.6899999976158142},{"id":"https://openalex.org/keywords/naive-bayesian-classifier","display_name":"naive Bayesian classifier","score":0.8209999799728394},{"id":"https://openalex.org/keywords/keyword-based-filtering","display_name":"keyword-based filtering","score":0.9290000200271606},{"id":"https://openalex.org/keywords/training-corpus-size","display_name":"training corpus size","score":0.902999997138977},{"id":"https://openalex.org/keywords/lemmatization","display_name":"lemmatization","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292648792266846},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7438605427742004},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4973173439502716},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49511972069740295},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4946129024028778},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4902835190296173},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48455873131752014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4472730755805969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44009581208229065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4349813461303711},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.419671893119812},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.16898587346076965},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07525721192359924},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/345508.345569","doi":"https://doi.org/10.1145/345508.345569","is_oa":true,"landing_page_url":"https://doi.org/10.1145/345508.345569","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/345508.345569","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:cs/0008019","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/cs/0008019","pdf_url":"https://arxiv.org/pdf/cs/0008019","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.8665","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.8665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/personal/Carl_Staelin/cs236601/androutsopoulos2000.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.cs/0008019","doi":"https://doi.org/10.48550/arxiv.cs/0008019","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.cs/0008019","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/345508.345569","doi":"https://doi.org/10.1145/345508.345569","is_oa":true,"landing_page_url":"https://doi.org/10.1145/345508.345569","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/345508.345569","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2085302848.pdf","grobid_xml":"https://content.openalex.org/works/W2085302848.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W140219282","https://openalex.org/W148103248","https://openalex.org/W195364088","https://openalex.org/W1493526108","https://openalex.org/W1507029541","https://openalex.org/W1587328194","https://openalex.org/W1625504505","https://openalex.org/W1638659076","https://openalex.org/W1648885110","https://openalex.org/W1813610639","https://openalex.org/W1817561967","https://openalex.org/W1956559956","https://openalex.org/W1992379233","https://openalex.org/W2036882650","https://openalex.org/W2043772506","https://openalex.org/W2060216474","https://openalex.org/W2089185211","https://openalex.org/W2094934653","https://openalex.org/W2097847889","https://openalex.org/W2111705563","https://openalex.org/W2124436456","https://openalex.org/W2157695030","https://openalex.org/W2325227998","https://openalex.org/W3016210511","https://openalex.org/W3151392175","https://openalex.org/W4238546739","https://openalex.org/W4247570771"],"related_works":["https://openalex.org/W2107555749","https://openalex.org/W2120011452","https://openalex.org/W4377970780","https://openalex.org/W7095803001","https://openalex.org/W2378997950","https://openalex.org/W2282355202","https://openalex.org/W2116791067","https://openalex.org/W1541184725","https://openalex.org/W2362590899","https://openalex.org/W1585280874"],"abstract_inverted_index":{"The":[0],"growing":[1],"problem":[2],"of":[3,21,62,90,117,130],"unsolicited":[4],"bulk":[5],"e-mail,":[6],"also":[7],"known":[8],"as":[9],"\u201cspam\u201d,":[10],"has":[11,38],"generated":[12],"a":[13,43,59,120,131],"need":[14],"for":[15],"reliable":[16],"anti-spam":[17],"e-mail":[18,64,134],"filters.":[19],"Filters":[20],"this":[22,56],"type":[23],"have":[24,101],"so":[25],"far":[26],"been":[27,40,103],"based":[28],"mostly":[29],"on":[30,58],"manually":[31],"constructed":[32],"keyword":[33,124],"patterns.":[34],"An":[35],"alternative":[36],"approach":[37,57],"recently":[39],"proposed,":[41],"whereby":[42],"Naive":[44,110],"Bayesian":[45,111],"classifier":[46],"is":[47,113,128],"trained":[48],"automatically":[49],"to":[50,119],"detect":[51],"spam":[52],"messages.":[53],"We":[54,78],"test":[55],"large":[60],"collection":[61],"personal":[63],"messages,":[65],"which":[66,127],"we":[67],"make":[68],"publicly":[69],"available":[70],"in":[71,105,115],"\u201cencrypted\u201d":[72],"form":[73],"contributing":[74],"towards":[75],"standard":[76],"benchmarks.":[77],"introduce":[79],"appropriate":[80],"cost-sensitive":[81],"measures,":[82],"investigating":[83],"at":[84],"the":[85,88,109],"same":[86],"time":[87],"effect":[89],"attribute-set":[91],"size,":[92,94],"training-corpus":[93],"lemmatization,":[95],"and":[96,126],"stop":[97],"lists,":[98],"issues":[99],"that":[100,122],"not":[102],"explored":[104],"previous":[106],"experiments.":[107],"Finally,":[108],"filter":[112,121],"compared,":[114],"terms":[116],"performance,":[118],"uses":[123],"patterns,":[125],"part":[129],"widely":[132],"used":[133],"reader.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":28},{"year":2012,"cited_by_count":29}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}