{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:28:46Z","timestamp":1782959326249,"version":"3.54.5"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"vor","delay-in-days":300,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Applied Computational Intelligence and Soft Computing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Spam emails are still an immense cybersecurity problem since they frequently result in financial theft, data breaches, and a general drop in user confidence within online interaction mediums. Although conventional spam detection algorithms have been effective in the past, they frequently fail to identify the more complex and context\u2010aware strategies employed by contemporary spammers. In this work, we assessed how well both sophisticated large language models (LLMs) and traditional machine learning methods performed in the classification of spam communications. The Enron Spam dataset was used to train four baseline models: multinomial Na\u00efve Bayes (MNB), K\u2010nearest neighbors, support vector machine (SVM), and multilayer perceptron (MLP). With an accuracy of 98.45%, MLP was the most successful conventional model among all. We also investigated the potential of a suggested GPT\u20104o and a refined Bidirectional Encoder Representations from Transformers (BERT) model for spam identification. With an accuracy and F1\u2010score of 99.45%, the BERT model performed better than any other model, while the GPT\u20104o model also produced impressive results with an accuracy of 98.77%. We verified all models on other datasets, such as SMS Spam, SpamAssassin, and Ling\u2010Spam, to make sure our results were not dataset specific. This made it easier to see how consistent and flexible they were with various layouts and literary approaches. The impact of activation functions in the BERT model was also investigated. Its ongoing usage in transformer\u2010based systems was supported by the minor performance advantage that the GELU activation function provided over ReLU. Lastly, to increase the statistical validity of our findings, we applied 5\u2010fold cross\u2010validation. All things considered, this research demonstrates how well LLMs, especially refined BERT, handle intricate linguistic structures and enhance spam detection mechanisms. However, it also demonstrates that MLP may still be a sensible option when computing assets are few.<\/jats:p>","DOI":"10.1155\/acis\/7032960","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T01:56:28Z","timestamp":1761702988000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Leveraging Large Language Model on Spam Email Detection and Classification"],"prefix":"10.1155","volume":"2025","author":[{"given":"Charles Okechukwu","family":"Ugwunna","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7965-2823","authenticated-orcid":false,"given":"Ibidun Christiana","family":"Obagbuwa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayowa Samuel","family":"Obadina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ifeanyi Godspower","family":"Akawuku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kingsley Chiwuike","family":"Ukaoha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,10,28]]},"reference":[{"key":"e_1_2_12_1_2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7710005"},{"key":"e_1_2_12_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcce.2024.01.002"},{"key":"e_1_2_12_3_2","unstructured":"Radicati Group Email Statistics Report 2023 https:\/\/www.radicati.com\/?p=18089."},{"key":"e_1_2_12_4_2","doi-asserted-by":"crossref","unstructured":"AlswailemAA.B. AlrumayhN. andAlsedraniA. Detecting Phishing Websites Using Machine Learning 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS) 2019 Riyadh Saudi Arabia 1\u20136 https:\/\/doi.org\/10.1109\/CAIS.2019.8769571 2-s2.0-85073896826.","DOI":"10.1109\/CAIS.2019.8769571"},{"key":"e_1_2_12_5_2","unstructured":"SidorovA. PamukS. and&ZhilaevM. Detection of Manipulative Language in Persuasive Messages Using NLP Techniques International Conference on Application of Natural Language Processing and Information Retrieval 2019 Springer 202\u2013211."},{"key":"e_1_2_12_6_2","unstructured":"LiQ. HongJ. XieC. TanJ. XinR. HouJ.et al. LLM-PBE: Assessing Data Privacy in Large Language Models arXiv Preprint arXiv:2408.12787 (2024)."},{"key":"e_1_2_12_7_2","doi-asserted-by":"crossref","unstructured":"LiL.andLiJ. Dimerization of Transmembrane Proteins in Cancer Immunotherapy Membranes 13 2023 Ieee 4th International Conference on Pattern Recognition and Machine Learning (PRML) August 2023 no. 4 393\u2013400 https:\/\/doi.org\/10.3390\/membranes13040393.","DOI":"10.1109\/PRML59573.2023.10348229"},{"key":"e_1_2_12_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.03.107"},{"key":"e_1_2_12_9_2","unstructured":"SahmoudT.andMikkiD. M. Spam Detection Using Bert 2022."},{"key":"e_1_2_12_10_2","doi-asserted-by":"crossref","unstructured":"TidaV. S.andHsuS. Universal Spam Detection Using Transfer Learning of Bert Model 2022.","DOI":"10.24251\/HICSS.2022.921"},{"key":"e_1_2_12_11_2","doi-asserted-by":"publisher","DOI":"10.47852\/bonviewJCCE2202192"},{"key":"e_1_2_12_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13112034"},{"key":"e_1_2_12_13_2","article-title":"An Improved Transformer-Based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach","author":"Jamal S.","year":"2023","journal-title":"Arxiv Preprint Arxiv:2311.04913"},{"key":"e_1_2_12_14_2","article-title":"Revolutionizing Cyber Threat Detection With Large Language Models","author":"Ferrag M. A.","year":"2023","journal-title":"Arxiv Preprint Arxiv:2306.14263"},{"key":"e_1_2_12_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/make6010018"},{"key":"e_1_2_12_16_2","article-title":"Chatspamdetector: Leveraging Large Language Models for Effective Phishing Email Detection","author":"Koide T.","year":"2024","journal-title":"Arxiv Preprint Arxiv:2402.18093"},{"key":"e_1_2_12_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108259"},{"key":"e_1_2_12_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"e_1_2_12_19_2","article-title":"Large Language Model Lateral Spear Phishing: A Comparative Study in Large-Scale Organizational Settings","author":"Bethany M.","year":"2024","journal-title":"Arxiv Preprint Arxiv:2401.09727"},{"key":"e_1_2_12_20_2","article-title":"An Explainable Transformer-Based Model for Phishing Email Detection: A Large Language Model Approach","author":"Uddin M. A.","year":"2024","journal-title":"Arxiv Preprint Arxiv:2402.13871"},{"key":"e_1_2_12_21_2","doi-asserted-by":"crossref","unstructured":"ChatautR. GyawaliP. K. andUsmanY. Can AI Keep you Safe? A Study of Large Language Models for Phishing Detection 2024 Ieee 14th Annual Computing and Communication Workshop and Conference (CCWC) January 2024 IEEE 0548\u20130554 https:\/\/doi.org\/10.1109\/CCWC60891.2024.10427626.","DOI":"10.1109\/CCWC60891.2024.10427626"},{"key":"e_1_2_12_22_2","article-title":"Prompted Contextual Vectors for Spear-Phishing Detection","author":"Nahmias D.","year":"2024","journal-title":"Arxiv Preprint Arxiv:2402.08309"},{"key":"e_1_2_12_23_2","unstructured":"MotlaghF. N. HajizadehM. MajdM. NajafiP. ChengF. andMeinelC. Large Language Models in Cybersecurity: State-of-The-Art 2024."},{"key":"e_1_2_12_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05643-7_25"},{"key":"e_1_2_12_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11132053"},{"key":"e_1_2_12_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/dasa54658.2022.9765017"},{"key":"e_1_2_12_27_2","doi-asserted-by":"publisher","DOI":"10.1177\/13621688211066997"},{"key":"e_1_2_12_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aci.2020.01.002"},{"key":"e_1_2_12_29_2","doi-asserted-by":"publisher","DOI":"10.1108\/jsit-11-2017-0105"},{"key":"e_1_2_12_30_2","doi-asserted-by":"publisher","DOI":"10.7176\/jep\/10-19-03"},{"key":"e_1_2_12_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10060668"},{"key":"e_1_2_12_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2019.e01802"},{"key":"e_1_2_12_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0658-2"},{"key":"e_1_2_12_34_2","unstructured":"Enron_spam 2024 https:\/\/huggingface.co\/datasets\/SetFit\/enron_spam."},{"key":"e_1_2_12_35_2","unstructured":"Enron_spam_data 2021 https:\/\/github.com\/MWiechmann\/enron_spam_data?tab=readme-ov-file#readme."},{"key":"e_1_2_12_36_2","unstructured":"DevlinJ. ChangM. LeeK. andToutanovaK. Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding 2018."}],"container-title":["Applied Computational Intelligence and Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/acis\/7032960","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/acis\/7032960","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/acis\/7032960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T11:48:20Z","timestamp":1772970500000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/acis\/7032960"}},"subtitle":[],"editor":[{"given":"Anandakumar","family":"Haldorai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/acis\/7032960"],"URL":"https:\/\/doi.org\/10.1155\/acis\/7032960","archive":["Portico"],"relation":{},"ISSN":["1687-9724","1687-9732"],"issn-type":[{"value":"1687-9724","type":"print"},{"value":"1687-9732","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-01-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"7032960"}}