{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:41:52Z","timestamp":1776127312768,"version":"3.50.1"},"reference-count":38,"publisher":"Tech Science Press","issue":"2","license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"vor","delay-in-days":328,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2024]]},"DOI":"10.32604\/cmc.2024.057279","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T10:39:00Z","timestamp":1731494340000},"page":"3395-3412","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":21,"title":["Comparative Analysis of Machine Learning Algorithms for Email Phishing Detection Using TF-IDF, Word2Vec, and BERT"],"prefix":"10.32604","volume":"81","author":[{"given":"Arar Al","family":"Tawil","sequence":"first","affiliation":[]},{"given":"Laiali","family":"Almazaydeh","sequence":"additional","affiliation":[]},{"given":"Doaa","family":"Qawasmeh","sequence":"additional","affiliation":[]},{"given":"Baraah","family":"Qawasmeh","sequence":"additional","affiliation":[]},{"given":"Mohammad","family":"Alshinwan","sequence":"additional","affiliation":[]},{"given":"Khaled","family":"Elleithy","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2024]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"2320","DOI":"10.12928\/telkomnika.v18i5.15911","article-title":"An overview of Internet of Things","volume":"18","author":"Villamil","year":"2020","journal-title":"Telkomnika (Telecommunication Computing Electronics and Control)"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.4946","article-title":"An overview of Internet of Things (IoT): Architectural aspects, challenges, and protocols","volume":"32","author":"Gupta","year":"2020","journal-title":"Concurr. Comput."},{"key":"ref3","doi-asserted-by":"crossref","first-page":"8176","DOI":"10.1016\/j.egyr.2021.08.126","article-title":"A comprehensive review study of cyber-attacks and cyber security; Emerging trends and recent developments","volume":"7","author":"Li","year":"2021","journal-title":"Energy Rep."},{"key":"ref4","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1108\/ICS-09-2022-0147","article-title":"Cyber terrorism cases and stock market valuation effects","volume":"31","author":"Smith","year":"2023","journal-title":"Inf Comput. Secur."},{"key":"ref5","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s42979-021-00535-6","article-title":"Deep cybersecurity: A comprehensive overview from neural network and deep learning perspective","volume":"2","author":"Sarker","year":"2021","journal-title":"SN Comput. Sci."},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2019.101677","article-title":"Cybersecurity for industrial control systems: A survey","volume":"89","author":"Bhamare","year":"2020","journal-title":"Comput. Secur."},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1093\/cybsec\/tyab005","article-title":"Simulation for cybersecurity: State of the art and future directions","volume":"7","author":"Kavak","year":"2021","journal-title":"J. Cybersecur."},{"key":"ref8","first-page":"57","article-title":"Machine learning in cybersecurity: A comprehensive survey","volume":"19","author":"Dasgupta","year":"2022","journal-title":"The J. Def. Model. Simul."},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.3390\/en13102509","article-title":"Performance comparison and current challenges of using machine learning techniques in cybersecurity","volume":"13","author":"Shaukat","year":"2020","journal-title":"Energies"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijcip.2022.100547","article-title":"Machine learning for cybersecurity in smart grids: A comprehensive review-based study on methods, solutions, and prospects","volume":"38","author":"Berghout","year":"2022","journal-title":"Int. J. Crit. Infrastruct. Prot."},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.3390\/app10175811","article-title":"A systematic review of defensive and offensive cybersecurity with machine learning","volume":"10","author":"Aiyanyo","year":"2020","journal-title":"Appl. Sci."},{"key":"ref12","series-title":"2021 12th Int. Conf. Inf. Commun. Syst. (ICICS)","first-page":"147","article-title":"URL phishing detection using machine learning techniques based on URLs lexical analysis","author":"Abutaha","year":"May 2021"},{"key":"ref13","series-title":"Proc. Anti-Phish. Work. Groups 2nd Annual eCrime Res. Summit.","first-page":"60","article-title":"A comparison of machine learning techniques for phishing detection","author":"Abu-Nimeh","year":"Oct. 2007"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"262","DOI":"10.35925\/j.multi.2020.4.30","article-title":"Analyzing and predicting spear-phishing using machine learning methods","volume":"10","author":"Samad","year":"2020","journal-title":"Multidiszciplin\u00e1ris Tudom\u00e1nyok"},{"key":"ref15","first-page":"1","article-title":"Detection of phishing emails using machine learning, deep learning","volume":"183","author":"Rathee","year":"2022","journal-title":"Int. J. Comput. Appl."},{"key":"ref16","series-title":"Proc. 1st Anti-Phish. Shared Pilot 4th ACM Int. Workshop Secur. Priv. Analy. (IWSPA 2018)","first-page":"1","article-title":"Machine learning based phishing E-mail detection","author":"Unnithan","year":"2018"},{"key":"ref17","series-title":"Proc. 1st Anti-Phishing Shared Task Pilot 4th ACM IWSPA Co-Located 8th ACM Conf. Data Appl. Secur. Priv. (CODASPY 2018)","article-title":"A machine learning approach towards phishing email detection CEN-Security@IWSPA 2018","author":"Harikrishnan","year":"Mar. 2018"},{"key":"ref18","first-page":"21","article-title":"Phishing detection in E-mails using machine learning","volume":"12","author":"Rawal","year":"Oct. 2017","journal-title":"Int. J. Appl. Inf. Syst."},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.3390\/app13095275","article-title":"A phishing-attack-detection model using natural language processing and deep learning","volume":"13","author":"Benavides-Astudillo","year":"Apr. 2023","journal-title":"Appl. Sci."},{"key":"ref20","unstructured":"Phishing_Mail, \u201cKaggle,\u201d Accessed: Jul. 13, 2023. [Online]. Available: https:\/\/www.kaggle.com\/datasets\/somumourya\/fishing-mail"},{"key":"ref21","series-title":"Proc. Int. Conf. Smart Technol. Comput., Electr. Electron. (ICSTCEE)","first-page":"391","article-title":"Phishing detection using random forest, SVM and neural network with backpropagation","author":"Sindhu","year":"2020"},{"key":"ref22","first-page":"120","article-title":"Identification of phishing attack in websites using random forest-SVM hybrid model","volume":"941","author":"Pandey","year":"2020","journal-title":"Proc. 18th Int. Conf. Intell. Syst. Des. Appl. (ISDA 2018)"},{"key":"ref23","first-page":"43","article-title":"Applying machine learning algorithms for detecting phishing websites: Applications of SVM, KNN, decision trees, and random forests","volume":"6","author":"Kayode-Ajala","year":"2022","journal-title":"Int. J. Inf. Cybersecur."},{"key":"ref24","first-page":"59","article-title":"PDMLP: Phishing detection using multilayer perceptron","volume":"12","author":"Al-Ahmadi","year":"2020","journal-title":"Int. J. Netw. Secur. Appl. (IJNSA)"},{"key":"ref25","first-page":"3353","article-title":"Efficient prediction of phishing websites using multilayer perceptron (MLP)","volume":"98","author":"Odeh","year":"2020","journal-title":"J. Theor. Appl. Inf. Technol."},{"key":"ref26","first-page":"1245","article-title":"Performance evaluation of logistic regression and neural network for credit risk assessment","volume":"9","author":"Joshi","year":"Feb. 2021","journal-title":"Int. J. Eng. Adv. Technol. (IJEAT)"},{"key":"ref27","unstructured":"J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, \u201cBERT: Pre-training of deep bidirectional transformers for language understanding,\u201d 2019, arXiv:1810.04805."},{"key":"ref28","unstructured":"Y. Liu et al., \u201cRoBERTa: A robustly optimized BERT pretraining approach,\u201d 2019, arXiv:1907.11692."},{"key":"ref29","unstructured":"V. Sanh, L. Debut, J. Chaumond, and T. Wolf, \u201cDistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter,\u201d 2019, arXiv:1910.01108."},{"key":"ref30","unstructured":"Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma and R. Soricut, \u201cALBERT: A lite BERT for self-supervised learning of language representations,\u201d 2020, arXiv:1909.11942."},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A review on evaluation metrics for data classification evaluations","volume":"5","author":"Hossin","year":"2015","journal-title":"Int. J. Data Min. Knowl. Manag. Process"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"65","DOI":"10.3991\/ijoe.v19i04.36099","article-title":"Clinical text classification with word representation features and machine learning algorithms","volume":"19","author":"Almazaydeh","year":"Apr. 2023","journal-title":"Int. J. Online Biomed. Eng."},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"A. Nayak, H. Timmapathini, K. Ponnalagu, and V. Gopalan Venkoparao, \u201cDomain adaptation challenges of BERT in tokenization and sub-word representations of out-of-vocabulary words,\u201d presented at the 1st Workshop Insights Negat. Results NLP, Nov. 2020, pp. 1\u20135.","DOI":"10.18653\/v1\/2020.insights-1.1"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"367","DOI":"10.3390\/make6010018","article-title":"Prompt engineering or fine-tuning? A case study on phishing detection with large language models","volume":"6","author":"Trad","year":"2024","journal-title":"Mach. Learn. Knowl. Extract."},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3434237","article-title":"A comprehensive survey on word representation models: From classical to state-of-the-art word representation language models","volume":"20","author":"Naseem","year":"2021","journal-title":"Trans. Asian Low-Res. Lang. Inf. Process."},{"key":"ref36","first-page":"123","author":"Jones","year":"1988","journal-title":"A Statistical Interpretation of Term Specificity and Its Application in Retrieval"},{"key":"ref37","series-title":"Proc. 1st Int. Conf. Learn. Represent. (ICLR 2013)","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref38","series-title":"Proc. 2nd IEEE Int. Conf. Comput. Commun. (ICCC)","first-page":"1195","article-title":"Short text classification based on Wikipedia and Word2vec","author":"Liu","year":"2016"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.techscience.com\/files\/cmc\/2024\/TSP_CMC-81-2\/TSP_CMC_57279\/TSP_CMC_57279.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T04:22:50Z","timestamp":1741321370000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v81n2\/58675"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024]]},"published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2024.057279","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2024-08-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-15","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-18","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}