{"id":"https://openalex.org/W3111551806","doi":"https://doi.org/10.1109/access.2020.3043396","title":"The Answer is in the Text: Multi-Stage Methods for Phishing Detection Based on Feature Engineering","display_name":"The Answer is in the Text: Multi-Stage Methods for Phishing Detection Based on Feature Engineering","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3111551806","doi":"https://doi.org/10.1109/access.2020.3043396","mag":"3111551806"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3043396","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3043396","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09288667.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09288667.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073418708","display_name":"\u00c9der Souza Gualberto","orcid":"https://orcid.org/0000-0002-2917-3605"},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]},{"id":"https://openalex.org/I71346753","display_name":"National Institute of Telecommunications","ror":"https://ror.org/0378w3a30","country_code":"BR","type":"facility","lineage":["https://openalex.org/I71346753"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Eder Souza Gualberto","raw_affiliation_strings":["Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil","Superintendence of Information Management, National Agency of Telecommunications, Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2917-3605","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I150729083"]},{"raw_affiliation_string":"Superintendence of Information Management, National Agency of Telecommunications, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I71346753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056962045","display_name":"Rafael T. de Sousa","orcid":"https://orcid.org/0000-0003-1101-3029"},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rafael Timoteo De Sousa","raw_affiliation_strings":["Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-1101-3029","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I150729083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047982490","display_name":"Thiago Pereira De Brito Vieira","orcid":"https://orcid.org/0000-0003-0512-374X"},"institutions":[{"id":"https://openalex.org/I71346753","display_name":"National Institute of Telecommunications","ror":"https://ror.org/0378w3a30","country_code":"BR","type":"facility","lineage":["https://openalex.org/I71346753"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thiago Pereira De Brito Vieira","raw_affiliation_strings":["Superintendence of Information Management, National Agency of Telecommunications, Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-0512-374X","affiliations":[{"raw_affiliation_string":"Superintendence of Information Management, National Agency of Telecommunications, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I71346753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069416979","display_name":"Jo\u00e3o Paulo C. L. da Costa","orcid":"https://orcid.org/0000-0002-8616-4924"},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]},{"id":"https://openalex.org/I4210088033","display_name":"Hamm-Lippstadt University of Applied Sciences","ror":"https://ror.org/001rdde17","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210088033"]}],"countries":["BR","DE"],"is_corresponding":false,"raw_author_name":"Joao Paulo Carvalho Lustosa Da Costa","raw_affiliation_strings":["Department 2 in Lippstadt, Hamm-Lippstadt University of Applied Sciences, Hamm, Germany","Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-8616-4924","affiliations":[{"raw_affiliation_string":"Department 2 in Lippstadt, Hamm-Lippstadt University of Applied Sciences, Hamm, Germany","institution_ids":["https://openalex.org/I4210088033"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I150729083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035235399","display_name":"Cl\u00e1udio Gottschalg Duque","orcid":"https://orcid.org/0000-0003-3558-466X"},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Claudio Gottschalg Duque","raw_affiliation_strings":["Faculty of Information Science, University of Bras\u00edlia, Bras\u00edlia, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science, University of Bras\u00edlia, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I150729083"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":6.684,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.96960019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"223529","last_page":"223547"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9972000122070312,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.8423218727111816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252933025360107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6754698753356934},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6296173930168152},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6072770357131958},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5423676371574402},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5056326389312744},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.49402695894241333},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.453361839056015},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45333346724510193},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3846331238746643},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.21364033222198486},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10211372375488281}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.8423218727111816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252933025360107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6754698753356934},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6296173930168152},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6072770357131958},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5423676371574402},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5056326389312744},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.49402695894241333},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.453361839056015},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45333346724510193},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3846331238746643},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.21364033222198486},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10211372375488281},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3043396","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3043396","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09288667.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:67f66adf564d46f7b25c48416498c5e2","is_oa":true,"landing_page_url":"https://doaj.org/article/67f66adf564d46f7b25c48416498c5e2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 223529-223547 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3043396","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3043396","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09288667.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G1571634718","display_name":null,"funder_award_id":"303343/2017-6 PQ-2","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G1665807523","display_name":null,"funder_award_id":"465741/2014-2 INCT","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G2604241884","display_name":null,"funder_award_id":"2019-5","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G2797333373","display_name":null,"funder_award_id":"88887.144009/2017-00","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G2823776494","display_name":null,"funder_award_id":"88887","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G3189284257","display_name":null,"funder_award_id":"0193.001366/2016","funder_id":"https://openalex.org/F4320323350","funder_display_name":"Funda\u00e7\u00e3o de Apoio \u00e0 Pesquisa do Distrito Federal"},{"id":"https://openalex.org/G3737694138","display_name":null,"funder_award_id":"465741/2014-2","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3812954411","display_name":null,"funder_award_id":"312180/2019-5","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G4246447654","display_name":null,"funder_award_id":"23038","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G4311951901","display_name":null,"funder_award_id":"2017-6","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G5492504476","display_name":null,"funder_award_id":"2014-2","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G5924580993","display_name":null,"funder_award_id":"BRICS 2017-591 LargEWiN","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G6934673299","display_name":null,"funder_award_id":"23038.007604/2014-69","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G6946261117","display_name":null,"funder_award_id":"303343/2017-6","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G7431043233","display_name":null,"funder_award_id":"88887.144009/2017-00","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G7566324240","display_name":null,"funder_award_id":"0193.001365/2016","funder_id":"https://openalex.org/F4320323350","funder_display_name":"Funda\u00e7\u00e3o de Apoio \u00e0 Pesquisa do Distrito Federal"},{"id":"https://openalex.org/G8091168005","display_name":null,"funder_award_id":"312180/2019-5 PQ-2","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320323350","display_name":"Funda\u00e7\u00e3o de Apoio \u00e0 Pesquisa do Distrito Federal","ror":"https://ror.org/04djvx395"},{"id":"https://openalex.org/F4320324004","display_name":"Forskningsr\u00e5det om H\u00e4lsa, Arbetsliv och V\u00e4lf\u00e4rd","ror":"https://ror.org/02d290r06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3111551806.pdf","grobid_xml":"https://content.openalex.org/works/W3111551806.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W150462035","https://openalex.org/W298402441","https://openalex.org/W1506806321","https://openalex.org/W1534408902","https://openalex.org/W1555148682","https://openalex.org/W1558416165","https://openalex.org/W1574901103","https://openalex.org/W1662133657","https://openalex.org/W1680622244","https://openalex.org/W1732828232","https://openalex.org/W1973942085","https://openalex.org/W1983578042","https://openalex.org/W2002964284","https://openalex.org/W2011211026","https://openalex.org/W2020648356","https://openalex.org/W2027558733","https://openalex.org/W2071254787","https://openalex.org/W2072981546","https://openalex.org/W2113449956","https://openalex.org/W2118023920","https://openalex.org/W2134750673","https://openalex.org/W2137346077","https://openalex.org/W2142063301","https://openalex.org/W2144006819","https://openalex.org/W2147152072","https://openalex.org/W2148403395","https://openalex.org/W2157213381","https://openalex.org/W2158997610","https://openalex.org/W2167277498","https://openalex.org/W2186649401","https://openalex.org/W2275092079","https://openalex.org/W2295598076","https://openalex.org/W2325170445","https://openalex.org/W2394758690","https://openalex.org/W2497967381","https://openalex.org/W2531813938","https://openalex.org/W2600150124","https://openalex.org/W2605725913","https://openalex.org/W2606089314","https://openalex.org/W2606751384","https://openalex.org/W2613526883","https://openalex.org/W2747198373","https://openalex.org/W2783862767","https://openalex.org/W2794598542","https://openalex.org/W2794616902","https://openalex.org/W2809613546","https://openalex.org/W2888558158","https://openalex.org/W2888921359","https://openalex.org/W2899780866","https://openalex.org/W2907351452","https://openalex.org/W2913458421","https://openalex.org/W2938051913","https://openalex.org/W2943848461","https://openalex.org/W2944103016","https://openalex.org/W2962880866","https://openalex.org/W2968485626","https://openalex.org/W2990168612","https://openalex.org/W2998216295","https://openalex.org/W3003474246","https://openalex.org/W3006834142","https://openalex.org/W3016685695","https://openalex.org/W3018800955","https://openalex.org/W3036541468","https://openalex.org/W3037109418","https://openalex.org/W3102476541","https://openalex.org/W3145506661","https://openalex.org/W3217529127","https://openalex.org/W4205687621","https://openalex.org/W4210984920","https://openalex.org/W4212863985","https://openalex.org/W4213009331","https://openalex.org/W4285719527","https://openalex.org/W4288358820","https://openalex.org/W6680864307","https://openalex.org/W6686996348","https://openalex.org/W6728482419","https://openalex.org/W6755964857","https://openalex.org/W6761397235","https://openalex.org/W6761990011","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W2782609208","https://openalex.org/W3088188605","https://openalex.org/W4388745254","https://openalex.org/W2980082554","https://openalex.org/W1517228774","https://openalex.org/W2767419625","https://openalex.org/W2389704471","https://openalex.org/W2117019857","https://openalex.org/W20047544","https://openalex.org/W1980222719"],"abstract_inverted_index":{"A":[0],"phishing":[1,71,83,241],"attack":[2],"is":[3],"a":[4,17,27,44,78,253],"threat":[5],"based":[6],"on":[7],"fraudulent":[8],"communication,":[9],"usually":[10],"by":[11],"e-mail,":[12],"where":[13],"the":[14,38,118,127,130,134,138,143,147,163,166,170,173,182,185,200,220,225,233,238],"cybercriminals,":[15],"impersonating":[16],"trusted":[18],"person":[19],"or":[20,72],"organization,":[21],"try":[22],"to":[23,47,57,66,81,141,209],"lure":[24],"and":[25,90,115,117,137,155,172,202,224,259],"coax":[26],"target.":[28],"Phishing":[29,227],"detection":[30,242],"approaches":[31],"that":[32,177],"obtain":[33],"highly":[34],"representational":[35],"features":[36,53,258],"from":[37,181],"text":[39,234],"of":[40,98,120,126,165,168,175,212,257],"these":[41,49,52],"e-mails":[42],"are":[43],"suitable":[45],"strategy":[46],"counter":[48],"threats":[50],"since":[51],"can":[54],"be":[55,179],"used":[56],"train":[58],"machine":[59,91,205],"learning":[60,111,206],"algorithms,":[61,207],"thus":[62],"generating":[63],"models":[64],"able":[65],"classify":[67],"mail":[68],"samples":[69],"as":[70],"legitimate":[73],"messages.":[74],"This":[75],"paper":[76],"proposes":[77],"multi-stage":[79,95,240],"approach":[80,96,243],"detect":[82],"e-mail":[84,236],"attacks":[85],"using":[86],"natural":[87,102],"language":[88,103],"processing":[89],"learning.":[92],"The":[93],"proposed":[94,128,239],"consists":[97],"feature":[99,106,108,195],"engineering":[100],"within":[101],"processing,":[104],"lemmatization,":[105],"selection,":[107],"extraction,":[109],"improved":[110],"techniques":[112],"for":[113,216,247],"resampling":[114],"cross-validation,":[116],"configuration":[119],"hyperparameters.":[121],"We":[122],"present":[123],"two":[124],"methods":[125,161,192],"approach,":[129],"first":[131],"one":[132],"exploiting":[133],"Chi-Square":[135],"statistics":[136],"Mutual":[139],"Information":[140],"improve":[142],"dimensionality":[144],"reduction,":[145],"while":[146],"second":[148],"method":[149],"associates":[150],"Principal":[151],"Component":[152],"Analysis":[153,158],"(PCA)":[154],"Latent":[156],"Semantic":[157],"(LSA).":[159],"Both":[160],"handle":[162],"problems":[164],"\u201ccurse":[167],"dimensionality\u201d,":[169],"sparsity,":[171],"amount":[174],"information":[176],"must":[178],"obtained":[180],"context":[183],"in":[184,235],"Vector":[186],"Space":[187],"Model":[188],"(VSM)":[189],"representation.":[190],"These":[191],"yield":[193],"reduced":[194],"sets":[196],"that,":[197],"combined":[198],"with":[199,219],"XGBoost":[201],"Random":[203],"Forest":[204],"lead":[208],"an":[210,248],"F1-measure":[211],"100%":[213],"success":[214],"rate,":[215],"validation":[217],"tests":[218],"SpamAssassin":[221],"Public":[222],"Corpus":[223,228],"Nazario":[226],"datasets.":[229],"Even":[230],"considering":[231],"just":[232],"bodies,":[237],"outperforms":[244],"state-of-the-art":[245],"schemes":[246],"accredited":[249],"data":[250],"set,":[251],"requiring":[252],"much":[254],"smaller":[255],"number":[256],"presenting":[260],"lower":[261],"computational":[262],"cost.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}