{"id":"https://openalex.org/W3012043050","doi":"https://doi.org/10.29007/qshd","title":"A Study of Machine Learning Algorithms on Email Spam Classification","display_name":"A Study of Machine Learning Algorithms on Email Spam Classification","publication_year":2020,"publication_date":"2020-03-09","ids":{"openalex":"https://openalex.org/W3012043050","doi":"https://doi.org/10.29007/qshd","mag":"3012043050"},"language":"en","primary_location":{"id":"doi:10.29007/qshd","is_oa":true,"landing_page_url":"https://doi.org/10.29007/qshd","pdf_url":"https://easychair.org/publications/open/Jvsw","source":{"id":"https://openalex.org/S4220651395","display_name":"EPiC series in computing","issn_l":"2398-7340","issn":["2398-7340"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPiC Series in Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://easychair.org/publications/open/Jvsw","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024770838","display_name":"N Sutta","orcid":null},"institutions":[{"id":"https://openalex.org/I161165907","display_name":"Southeast Missouri State University","ror":"https://ror.org/010n41y16","country_code":"US","type":"education","lineage":["https://openalex.org/I161165907"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N Sutta","raw_affiliation_strings":["Department of Computer Science Southeast Missouri State University, Missouri, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Southeast Missouri State University, Missouri, U.S.A","institution_ids":["https://openalex.org/I161165907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382209","display_name":"Zhi Liu","orcid":"https://orcid.org/0000-0001-5346-7569"},"institutions":[{"id":"https://openalex.org/I161165907","display_name":"Southeast Missouri State University","ror":"https://ror.org/010n41y16","country_code":"US","type":"education","lineage":["https://openalex.org/I161165907"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Z Liu","raw_affiliation_strings":["Department of Computer Science Southeast Missouri State University, Missouri, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Southeast Missouri State University, Missouri, U.S.A","institution_ids":["https://openalex.org/I161165907"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071982811","display_name":"Xie Zhang","orcid":"https://orcid.org/0000-0003-3424-9253"},"institutions":[{"id":"https://openalex.org/I161165907","display_name":"Southeast Missouri State University","ror":"https://ror.org/010n41y16","country_code":"US","type":"education","lineage":["https://openalex.org/I161165907"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"X Zhang","raw_affiliation_strings":["Department of Computer Science Southeast Missouri State University, Missouri, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Southeast Missouri State University, Missouri, U.S.A","institution_ids":["https://openalex.org/I161165907"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161165907"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":null,"first_page":"170","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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":0.9998999834060669,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9957000017166138,"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/spamming","display_name":"Spamming","score":0.9153687953948975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8122037649154663},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6981196403503418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6190040111541748},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6022066473960876},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5203692317008972},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5159414410591125},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.5127907395362854},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.491496205329895},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3831239342689514},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.22837355732917786},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15883618593215942}],"concepts":[{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.9153687953948975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122037649154663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6981196403503418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6190040111541748},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6022066473960876},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5203692317008972},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5159414410591125},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.5127907395362854},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.491496205329895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3831239342689514},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.22837355732917786},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15883618593215942},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.29007/qshd","is_oa":true,"landing_page_url":"https://doi.org/10.29007/qshd","pdf_url":"https://easychair.org/publications/open/Jvsw","source":{"id":"https://openalex.org/S4220651395","display_name":"EPiC series in computing","issn_l":"2398-7340","issn":["2398-7340"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPiC Series in Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.29007/qshd","is_oa":true,"landing_page_url":"https://doi.org/10.29007/qshd","pdf_url":"https://easychair.org/publications/open/Jvsw","source":{"id":"https://openalex.org/S4220651395","display_name":"EPiC series in computing","issn_l":"2398-7340","issn":["2398-7340"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPiC Series in Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012043050.pdf","grobid_xml":"https://content.openalex.org/works/W3012043050.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W327991062","https://openalex.org/W1629485395","https://openalex.org/W2063252718","https://openalex.org/W2064615898","https://openalex.org/W2101919228","https://openalex.org/W2130624643","https://openalex.org/W2317643927","https://openalex.org/W2339021494","https://openalex.org/W2468185511","https://openalex.org/W2613526883","https://openalex.org/W2749511780","https://openalex.org/W4285719527","https://openalex.org/W6675580205","https://openalex.org/W6720039614"],"related_works":["https://openalex.org/W4200112873","https://openalex.org/W2955796858","https://openalex.org/W4224941037","https://openalex.org/W2004826645","https://openalex.org/W2943490005","https://openalex.org/W4401361218","https://openalex.org/W2003072179","https://openalex.org/W2034680797","https://openalex.org/W2964398403","https://openalex.org/W2967426019"],"abstract_inverted_index":{"Despite":[0],"the":[1,14,35,54,61,90,93,96,109,112,115,127],"fact":[2],"that":[3,89],"different":[4],"techniques":[5,33],"have":[6],"been":[7],"developed":[8],"to":[9,13,39],"filter":[10,42],"spam,":[11],"due":[12],"spammer\u2019s":[15],"rapid":[16],"adoption":[17],"of":[18,53,56,72,92,108],"new":[19],"spam":[20,28,43],"detection":[21],"techniques,":[22],"we":[23],"are":[24,34,67],"still":[25],"overwhelmed":[26],"with":[27,75,118],"emails.":[29,44],"Currently,":[30],"machine":[31],"learning":[32],"most":[36,107],"effective":[37],"ways":[38],"classify":[40],"and":[41,51,111],"In":[45],"this":[46],"paper,":[47],"a":[48],"comprehensive":[49],"comparison":[50],"analysis":[52],"performance":[55],"various":[57,70],"classification":[58,104],"models":[59,105,113,125],"on":[60],"2007":[62],"TREC":[63],"Public":[64],"Spam":[65],"Corpus":[66],"exhibited":[68],"in":[69,95,106],"cases":[71],"without":[73],"or":[74,83],"N-":[76],"Grams":[77],"as":[78,80],"well":[79],"using":[81,114,126],"separate":[82,128],"combined":[84,119],"datasets.":[85],"It":[86],"is":[87],"shown":[88],"inclusion":[91],"N-Grams":[94],"pre-processing":[97],"phase":[98],"provides":[99],"high":[100],"accuracy":[101],"results":[102,123],"for":[103],"cases,":[110],"split":[116],"approach":[117],"datasets":[120],"give":[121],"better":[122],"than":[124],"dataset.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}