{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:03:18Z","timestamp":1768518198023,"version":"3.49.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"DOI":"10.1186\/s40537-025-01176-9","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T10:53:05Z","timestamp":1747911185000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["BERT-GraphSAGE: hybrid approach to spam detection"],"prefix":"10.1186","volume":"12","author":[{"given":"F.","family":"Zouak","sequence":"first","affiliation":[]},{"given":"O.","family":"El Beqqali","sequence":"additional","affiliation":[]},{"given":"J.","family":"Riffi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"key":"1176_CR1","unstructured":"J\u00e1\u00f1ez-Martino F, Fidalgo E, Gonz\u00e1lez-Mart\u00ednez S, Velasco-Mata J. Classification of spam emails through hierarchical clustering and supervised learning. arXiv, 2020. http:\/\/arxiv.org\/abs\/2005.08773."},{"key":"1176_CR2","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-53970-2_4","volume-title":"Artificial intelligence and industrial applications","author":"G Hnini","year":"2021","unstructured":"Hnini G, Riffi J, Mahraz MA, Yahyaouy A, Tairi H. Spam filtering system based on nearest neighbor algorithms. In: Masrour T, El Hassani I, Cherrafi A, editors. Artificial intelligence and industrial applications. Cham: Springer International Publishing; 2021. p. 36\u201346."},{"key":"1176_CR3","doi-asserted-by":"publisher","DOI":"10.24843\/LKJITI.2017.v08.i03.p08","author":"AR Chrismanto","year":"2017","unstructured":"Chrismanto AR, Lukito Y. Identifikasi Komentar Spam Pada Instagram. Lontar Komput J Ilm Teknol Inf. 2017. https:\/\/doi.org\/10.24843\/LKJITI.2017.v08.i03.p08.","journal-title":"Lontar Komput J Ilm Teknol Inf"},{"key":"1176_CR4","doi-asserted-by":"publisher","first-page":"316","DOI":"10.18178\/ijmlc.2020.10.2.937","volume":"10","author":"S Douzi","year":"2020","unstructured":"Douzi S, AlShahwan FA, Lemoudden M, Ouahidi BE. Hybrid email spam detection model using artificial intelligence. Int J Mach Learn Comput. 2020;10:316\u201322. https:\/\/doi.org\/10.18178\/ijmlc.2020.10.2.937.","journal-title":"Int J Mach Learn Comput"},{"key":"1176_CR5","doi-asserted-by":"publisher","first-page":"012113","DOI":"10.1088\/1757-899X\/1022\/1\/012113","volume":"1022","author":"MV Madhavan","year":"2021","unstructured":"Madhavan MV, Pande S, Umekar P, Mahore T, Kalyankar D. Comparative analysis of detection of email spam with the aid of machine learning approaches. IOP Conf Ser Mater Sci Eng. 2021;1022:012113. https:\/\/doi.org\/10.1088\/1757-899X\/1022\/1\/012113.","journal-title":"IOP Conf Ser Mater Sci Eng"},{"key":"1176_CR6","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.procs.2021.03.107","volume":"184","author":"I AbdulNabi","year":"2021","unstructured":"AbdulNabi I, Yaseen Q. Spam email detection using deep learning techniques. Procedia Comput Sci. 2021;184:853\u20138. https:\/\/doi.org\/10.1016\/j.procs.2021.03.107.","journal-title":"Procedia Comput Sci"},{"key":"1176_CR7","doi-asserted-by":"publisher","unstructured":"Sahmoud T, Mikki M. Spam detection using BERT. arXiv, 2022. https:\/\/doi.org\/10.48550\/arXiv.2206.02443.","DOI":"10.48550\/arXiv.2206.02443"},{"key":"1176_CR8","doi-asserted-by":"publisher","unstructured":"Tida VS, Hy Hsu S. Universal spam detection using transfer learning of BERT Model, 2022. https:\/\/doi.org\/10.24251\/HICSS.2022.921.","DOI":"10.24251\/HICSS.2022.921"},{"key":"1176_CR9","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv. 2019. http:\/\/arxiv.org\/abs\/1810.04805."},{"key":"1176_CR10","unstructured":"Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space\u00a0. arXiv, 2013. http:\/\/arxiv.org\/abs\/1301.3781."},{"key":"1176_CR11","doi-asserted-by":"publisher","first-page":"152183","DOI":"10.1109\/ACCESS.2020.3017382","volume":"8","author":"L Cai","year":"2020","unstructured":"Cai L, Song Y, Liu T, Zhang K. A hybrid BERT model that incorporates label semantics via adjustive attention for multi-label text classification. IEEE Access. 2020;8:152183\u201392. https:\/\/doi.org\/10.1109\/ACCESS.2020.3017382.","journal-title":"IEEE Access"},{"key":"1176_CR12","doi-asserted-by":"publisher","unstructured":"Mardiansyah K, W Surya. Comparative analysis of ChatGPT-4 and google gemini for spam detection on the spamAssassin public mail corpus, 2024. https:\/\/doi.org\/10.21203\/rs.3.rs-4005702\/v1.","DOI":"10.21203\/rs.3.rs-4005702\/v1"},{"key":"1176_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/6737080","volume":"2022","author":"W Pan","year":"2022","unstructured":"Pan W, Li J, Gao L, Yue L, Yang Y, Deng L, Deng C. Semantic graph neural network: a conversion from spam email classification to graph classification. Sci Program. 2022;2022:1\u20138. https:\/\/doi.org\/10.1155\/2022\/6737080.","journal-title":"Sci Program"},{"key":"1176_CR14","doi-asserted-by":"crossref","unstructured":"Lin Y, Meng Y, Sun X, Han Q, Kuang K, Li J, Wu F. BertGCN: transductive text classification by combining GCN and BERT\u00a0. arXiv, 2022. http:\/\/arxiv.org\/abs\/2105.05727.","DOI":"10.18653\/v1\/2021.findings-acl.126"},{"key":"1176_CR15","doi-asserted-by":"publisher","unstructured":"Hamilton WL, Ying R, Leskovec J. Inductive representation learning on large graphs\u00a0. arXiv, 2018. https:\/\/doi.org\/10.48550\/arXiv.1706.02216.","DOI":"10.48550\/arXiv.1706.02216"},{"key":"1176_CR16","unstructured":"Nakajima H, Sasaki M. Text classification using a graph based on relationships between documents. In Proceedings of the 36th Pacific Asia Conference on Language, Information and Computation, Manila, Philippines, 2022; pp. 119\u2013125."},{"key":"1176_CR17","doi-asserted-by":"publisher","unstructured":"Xu X, Lyu L, Dong Y, Lu Y, Wang W, Jin H. SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attention. arXiv, 2023. https:\/\/doi.org\/10.48550\/arXiv.2301.12885.","DOI":"10.48550\/arXiv.2301.12885"},{"key":"1176_CR18","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I. Attention is all you need.\u00a0Advances in neural information processing systems, 2017;\u00a030."},{"key":"1176_CR19","doi-asserted-by":"publisher","unstructured":"Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P et al. Transformers: State-of-the-Art Natural Language Processing\u00a0. In: Qun Liu and David Schlangen (eds). Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations. Online: Association for Computational Linguistics, 2020; 38\u201345. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"1176_CR20","doi-asserted-by":"publisher","unstructured":"Linmei H, Yang T, Shi C, Ji H, Li X. Heterogeneous graph attention networks for semi-supervised short text classification\u00a0. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong, China: Association for Computational Linguistics, 2019; 4820\u201329. https:\/\/doi.org\/10.18653\/v1\/D19-1488.","DOI":"10.18653\/v1\/D19-1488"},{"key":"1176_CR21","unstructured":"The Enron-Spam datasets. https:\/\/www2.aueb.gr\/users\/ion\/data\/enron-spam\/. Accessed 6 Jul 2024."},{"key":"1176_CR22","doi-asserted-by":"publisher","DOI":"10.47852\/bonviewJCCE2202192","author":"Y Guo","year":"2022","unstructured":"University of Illinois Springfield, USA, Guo Y, Mustafaoglu Z, University of Illinois Springfield, USA, Koundal D, University of Petroleum and Energy Studies, India. Spam detection using bidirectional transformers and machine learning classifier algorithms. J Comput Cogn Eng. 2022. https:\/\/doi.org\/10.47852\/bonviewJCCE2202192.","journal-title":"J Comput Cogn Eng"},{"key":"1176_CR23","unstructured":"Index de \/old\/publiccorpus. https:\/\/spamassassin.apache.org\/old\/publiccorpus\/. Accessed 29 Jul 2024."},{"issue":"1","key":"1176_CR24","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1023\/A:1022948414856","volume":"6","author":"G Sakkis","year":"2003","unstructured":"Sakkis G, Androutsopoulos I, Paliouras G, Karkaletsis V, Spyropoulos CD, Stamatopoulos P. No title found. Inf Retrieval. 2003;6(1):49\u201373. https:\/\/doi.org\/10.1023\/A:1022948414856.","journal-title":"Inf Retrieval"},{"key":"1176_CR25","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-3-030-57024-8_7","volume-title":"Machine intelligence and big data analytics for cybersecurity applications","author":"S Srinivasan","year":"2021","unstructured":"Srinivasan S, Ravi V, Alazab M, Ketha S, Al-Zoubi AM, Kotti Padannayil S. Spam emails detection based on\u00a0distributed word embedding with\u00a0deep\u00a0learning. In: Maleh Y, Shojafar M, Alazab M, Baddi Y, editors. Machine intelligence and big data analytics for cybersecurity applications. Cham: Springer International Publishing; 2021. p. 161\u201389. https:\/\/doi.org\/10.1007\/978-3-030-57024-8_7."}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01176-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-025-01176-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01176-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T10:53:13Z","timestamp":1747911193000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-025-01176-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1176"],"URL":"https:\/\/doi.org\/10.1186\/s40537-025-01176-9","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,22]]},"assertion":[{"value":"18 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"128"}}