{"id":"https://openalex.org/W4406892715","doi":"https://doi.org/10.1109/csnet64211.2024.10851768","title":"Detecting Spam Emails Using Machine Learning and Lemmatization vs Traditional Methods","display_name":"Detecting Spam Emails Using Machine Learning and Lemmatization vs Traditional Methods","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4406892715","doi":"https://doi.org/10.1109/csnet64211.2024.10851768"},"language":"en","primary_location":{"id":"doi:10.1109/csnet64211.2024.10851768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csnet64211.2024.10851768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 8th Cyber Security in Networking Conference (CSNet)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100768181","display_name":"Jun Peng","orcid":"https://orcid.org/0000-0002-2337-5273"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jun Peng","raw_affiliation_strings":["Infocomm Technology Cluster, Singapore Institute of Technology,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Infocomm Technology Cluster, Singapore Institute of Technology,Singapore,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Derick Kwok","orcid":null},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Derick Kwok","raw_affiliation_strings":["Infocomm Technology Cluster, Singapore Institute of Technology,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Infocomm Technology Cluster, Singapore Institute of Technology,Singapore,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071022377","display_name":"Huaqun Guo","orcid":"https://orcid.org/0000-0001-6753-6537"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huaqun Guo","raw_affiliation_strings":["Infocomm Technology Cluster, Singapore Institute of Technology,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Infocomm Technology Cluster, Singapore Institute of Technology,Singapore,Singapore","institution_ids":["https://openalex.org/I168639165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100768181"],"corresponding_institution_ids":["https://openalex.org/I168639165"],"apc_list":null,"apc_paid":null,"fwci":1.5092,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88606191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.996999979019165,"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":0.996999979019165,"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":0.9825000166893005,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.944599986076355,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/lemmatisation","display_name":"Lemmatisation","score":0.8584937453269958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.819288432598114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5660993456840515},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.4767490327358246},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3837425708770752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3709483742713928},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.2722402811050415},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19626402854919434},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.17000332474708557}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.8584937453269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819288432598114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5660993456840515},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.4767490327358246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3837425708770752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3709483742713928},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.2722402811050415},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19626402854919434},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.17000332474708557}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/csnet64211.2024.10851768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csnet64211.2024.10851768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 8th Cyber Security in Networking Conference (CSNet)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/30225184","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/30225184","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2959529161","https://openalex.org/W2982605177","https://openalex.org/W4205899514","https://openalex.org/W4291700788","https://openalex.org/W4360585198","https://openalex.org/W4360994701","https://openalex.org/W4383745178"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3124131622","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Emails":[0],"are":[1],"a":[2,46,55,63,78,107],"common":[3],"method":[4,66,79,96,127,142],"of":[5,58,92,100,104,117,128,143],"communication":[6],"and":[7,102,137],"used":[8],"by":[9],"many":[10],"companies":[11],"for":[12,158],"public":[13],"facing":[14],"systems.":[15],"As":[16],"malicious":[17],"actors":[18],"send":[19],"spam":[20,111],"emails":[21],"to":[22,24,27,36,53,72,83,122],"try":[23],"gain":[25],"access":[26],"the":[28,74,90,159],"systems,":[29],"filters":[30],"must":[31],"be":[32,51],"put":[33],"in":[34],"place":[35],"filter":[37],"them":[38],"out.":[39],"Although":[40],"traditional":[41,126],"email":[42,129,138],"filtering":[43,130],"methods":[44,84,157],"exist,":[45],"machine":[47,64,87,155],"learning":[48,65,156],"approach":[49],"can":[50],"employed":[52],"attain":[54],"higher":[56],"accuracy":[57,99,152],"filtering.":[59],"This":[60,113,141],"paper":[61],"employs":[62],"Extra":[67,144],"Trees":[68,145],"Classifier":[69,146],"with":[70,106,147],"lemmatization":[71,148],"determine":[73],"benefit":[75],"that":[76],"such":[77],"will":[80],"have":[81],"compared":[82,121],"not":[85],"using":[86,131],"learning.":[88],"Through":[89],"results":[91],"our":[93],"testing,":[94],"this":[95],"achieved":[97],"an":[98,115],"98.16%":[101],"precision":[103],"94.30%":[105],"lemmatized":[108],"dataset":[109],"detecting":[110],"emails.":[112],"is":[114],"improvement":[116],"10.07<sup":[118],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">%</sup>":[120],"previous":[123],"study":[124],"employing":[125],"active":[132],"domain":[133],"name":[134],"service":[135],"data":[136],"reception":[139],"log.":[140],"also":[149],"achieves":[150],"better":[151],"than":[153],"other":[154],"same":[160],"dataset.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}