Sistem Penyaringan Spam Email Menggunakan Long Short Term Memory (LSTM)
DOI:
https://doi.org/10.29407/wcqeqj60Keywords:
Email, LSTM, Plugin, SpamAbstract
Email merupakan media komunikasi yang banyak digunakan, namun meningkatnya jumlah spam email menimbulkan gangguan dan risiko keamanan informasi. Pendekatan penyaringan spam konvensional masih memiliki keterbatasan dalam mengenali pola spam yang terus berkembang. Penelitian ini bertujuan untuk mengembangkan sistem penyaringan spam email menggunakan algoritma Long Short-Term Memory (LSTM) yang mampu mengklasifikasikan email spam dan non-spam berdasarkan isi pesan. Data penelitian berupa dataset email berlabel spam dan non-spam yang diproses melalui tahapan preprocessing teks, tokenisasi, padding sekuens, serta pelatihan model LSTM dengan mekanisme early stopping. Evaluasi kinerja model dilakukan menggunakan confusion matrix dan metrik accuracy, precision, recall, serta F1-score. Hasil pengujian menunjukkan bahwa model LSTM mencapai nilai akurasi sebesar 0,99 dengan nilai precision, recall, dan F1-score yang sama-sama tinggi pada kedua kelas, yang menandakan kemampuan klasifikasi yang sangat baik dan stabil. Model yang telah dilatih kemudian diimplementasikan ke dalam sistem penyaringan spam email berbasis web menggunakan Streamlit dan protokol IMAP. Hasil penelitian ini menunjukkan bahwa LSTM efektif dan aplikatif untuk digunakan sebagai sistem penyaringan spam email otomatis.
Downloads
References
[1] T. A. Almeida, J. María, G. Hidalgo, and T. P. Silva, “Towards SMS Spam Filtering : Results under a New Dataset,” vol. 2, no. 1, pp. 1–18.
[2] I. AbdulNabi and Q. Yaseen, “Spam email detection using deep learning techniques,” Procedia Comput. Sci., vol. 184, pp. 853–858, 2021.
[3] S. Wali, A. Alsudani, H. Ali, M. Nasrawi, M. Hasan, and A. Ghazikhani, “Enhancing Spam Detection : A Crow-Optimized FFNN with LSTM for Email Security,” pp. 28–39, 2024.
[4] H. A. M. Bert, “ScienceDirect Spam Spam Email Email Detection Detection Using Using Deep Deep Learning Learning Techniques Techniques,” Procedia Comput. Sci., vol. 184, no. 2019, pp. 853–858, 2021, doi: 10.1016/j.procs.2021.03.107.
[5] M. Al Kautsar, G. G. Setiaji, and A. Rifa, “BULLETIN OF COMPUTER SCIENCE RESEARCH Analisis Komparasi Kinerja LSTM dan CNN dalam Deteksi Spam Email Berbasis Deep learning,” vol. 5, no. 4, pp. 584–593, 2025, doi: 10.47065/bulletincsr.v5i4.572.
[6] D. Rizkiono, “Komparasi Deep Learning Dan Traditional Machine Learning Untuk Email Spam Filtering,” vol. 12, pp. 636–643, 2023.
[7] S. A. Aklani, H. Haeruddin, and N. Putri, “Implementasi Mail Gateway Security Dalam Meningkatkan Keamanan Email,” J. Inf. Syst. Manag., vol. 5, no. 2, pp. 150–155, 2024.
[8] A. Mustofa and S. Pradana, “Perbandingan Pengujian Deteksi Phising menggunakan Metode SVM dengan Kernel RBF dan Linear Comparison of Phishing Detection Tests using the SVM Method with RBF and Linear Kernels,” vol. 12, no. September, pp. 754–759, 2023.
[9] N. Adila, S. Khasanah, and T. Sutabri, “STRATEGI PERANCANGAN SISTEM AMAVIS DAN,” vol. 5, no. 2, pp. 154–166, 2023.
[10] A. Harbani and A. Sidiyantoro, “Implementasi Simple Mail Transfer Protocol Relay Pada Mail Gateway Untuk Menentukan Konten Email Spam,” vol. 12, no. 1, pp. 57–66, 2022, doi: 10.36350/jbs.v12i1.130
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mohammad Irfan Wahyudi, Muhammad Fernanda Mulya Putra
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
