Analisis Komparasi Kinerja LSTM dan CNN dalam Deteksi Spam Email Berbasis Deep learning
DOI:
https://doi.org/10.47065/bulletincsr.v5i4.572Keywords:
Spam Email; Deep Learning; CNN; LSTM; Text ClassificationAbstract
Spam email remains a critical issue in digital communication due to its potential misuse in spreading false information and online fraud. This study aims to evaluate and compare the performance of two deep learning models Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) for text-based spam email classification. The dataset used in this study was obtained from Kaggle and contains 5,572 labeled email entries categorized as spam and non-spam. The preprocessing stage included labeling, cleaning, lowercasing (casefolding), tokenization, stopword removal, and stemming. The data was split into training and testing sets with a 70:30 ratio. Both models were trained using the same configuration and evaluated using accuracy, loss, confusion matrix, and F1-score metrics. The results indicate that the LSTM model achieved the highest accuracy of 98.72% with a loss value of 0.0377, outperforming the CNN model, which achieved 87.78% accuracy and a loss of 0.3659. Based on these findings, LSTM demonstrated superior performance in detecting spam emails using text-based input. This research is expected to serve as a reference for developing more accurate and effective spam detection systems in the future.
Downloads
References
A. Muhaimin, I. A. Taufik, and D. D. Daniswara, “Pendeteksian Spam pada E-mail menggunakan Pendekatan Natural Language Processing,” Pros. Semin. Nas. Sains Data, vol. 3, no. 1, pp. 116–121, 2023, doi: 10.33005/senada.v3i1.90.
A. N. Salim, A. Adryani, and T. Sutabri, “Deteksi Email Spam dan Non-spam Berdasarkan Isi Konten Menggunakan Metode K-Nearest Neighbor dan Support Vector Machine,” Syntax Idea, vol. 6, no. 2, pp. 991–1001, 2024, doi: 10.46799/syntax-idea.v6i2.3052.
C. M. Bachri and W. Gunawan, “Deteksi Email Spam menggunakan Algoritma Convolutional Neural Network (CNN),” Edukasi dan Penelit. Inform., vol. 10, no. 1, pp. 88–94, 2024.
I. AbdulNabi and Q. Yaseen, “Spam email detection using deep learning techniques,” Procedia Computer Science, vol. 184, no. January 2021, pp. 853–858, 2021, doi: 10.1016/j.procs.2021.03.107.
E. al. Ratnam Dodda, “Precision in Classification: A Comparative Study of Logistic Regression, Naive Bayes, LSTM, and CNN for Spam Email Detection,” Int. J. Recent Innov. Trends Comput. Commun., vol. 11, no. 9, pp. 2276–2280, 2023, doi: 10.17762/ijritcc.v11i9.9233.
R. Approaches and G. Airlangga, “A Comparative Analysis of Deep learning Models for SMS Spam Detection : CNN-LSTM, CNN-GRU, and ResNet Approaches,” Journal of Computer Networks , Architecture and High Performance Computing, vol. 6, no. 4, pp. 1952–1960, 2024.
S. N. Saputra, G. G. Setiaji, and M. T. A. C. Widiyanto, “Perbandingan Kinerja RNN dan CNN Dalam Klasifikasi Sentimen Ulasan Pengguna Aplikasi di Play Store,” Journal of Computer System and Informatics (JoSYC), vol. 6, no. 1, pp. 349–362, 2024, doi: 10.47065/josyc.v6i1.6408.
A. Sheneamer, “Comparison of Deep learning and Traditional Methods for Email Spam Filtering,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 1, pp. 560–565, 2021, doi: 10.14569/IJACSA.2021.0120164.
H. Setiawan and D. Ariatmanto, “Analisis Perbandingan Algoritma Machine Learning Dan Deep learning Untuk Sentimen Analisis Teks Umpan Balik Tentang Evaluasi Pengajaran Dosen,” JSAI (Journal Sci. Appl. Informatics), vol. 7, no. 2, pp. 379–385, 2024, doi: 10.36085/jsai.v7i2.6572.
S. Govindan, A. F. A. Abidin, M. A. Mohamed, S. D. Mohd Satar, M. F. Abdul Kadir, and N. Abd Hamid, “Spam Detection Model Using Tensorflow and Deep learning Algorithm,” Malaysian J. Comput. Appl. Math., vol. 6, no. 2, pp. 11–21, 2023, doi: 10.37231/myjcam.2023.6.2.84.
B. A. Febryanto and I. Tahyudin, “Perbandingan Algoritma CNN, LSTM, FNN untuk Diagnosa Fibrosis Hati dengan Citra Medis,” Techno.Com, vol. 24, no. 1, pp. 41–55, 2025.
K. Thakur, M. L. Ali, M. A. Obaidat, and A. Kamruzzaman, “A Systematic Review on Deep-Learning-Based Phishing Email Detection,” Electron., vol. 12, no. 21, pp. 1–26, 2023, doi: 10.3390/electronics12214545.
S. Atawneh and H. Aljehani, “Phishing Email Detection Model Using Deep learning,” Electron., vol. 12, no. 20, 2023, doi: 10.3390/electronics12204261.
MR Adepu Rajesh and Dr Tryambak Hiwarkar, “Exploring Preprocessing Techniques for Natural LanguageText: A Comprehensive Study Using Python Code,” Int. J. Eng. Technol. Manag. Sci., vol. 7, no. 5, pp. 390–399, 2023, doi: 10.46647/ijetms.2023.v07i05.047.
F. Jáñez-Martino, R. Alaiz-Rodríguez, V. González-Castro, E. Fidalgo, and E. Alegre, “Classifying spam emails using agglomerative hierarchical clustering and a topic-based approach,” Appl. Soft Comput., vol. 139, p. 110226, 2023, doi: 10.1016/j.asoc.2023.110226.
N. C. Dewi and A. Qoiriah, “Implementasi Algoritma Jaro-Winkler Distance dan N-Gram untuk Deteksi dan Prediksi Perbaikan Kesalahan Penulisan Kata Bahasa Indonesia pada Karya Tulis Ilmiah Mahasiswa,” J. Informatics Comput. Sci., vol. 2, no. 03, pp. 169–177, 2021, doi: 10.26740/jinacs.v2n03.p169-177.
Y. A. Risqi and I. Susilawati, “Pemanfaatan Artificial Intelligence dan Cognitive Behavioral Therapy Untuk Pengembangan Chatbot Pembelajaran Matematika Sekolah Menengah,” Journal of Information System Research (JOSH), vol. 6, no. 2, 2025, doi: 10.47065/josh.v6i2.6523.
N. Nurwanda, N. Suarna, and W. Prihartono, “Penerapan NLP (Natural Language Processing) Dalam Analisis Sentimen Pengguna Telegram Di Playstore,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 2, pp. 1841–1846, 2024, doi: 10.36040/jati.v8i2.8469.
M. S. Anwar, I. Much, I. Subroto, and S. Mulyono, “Sistem Pencarian E-Journal Menggunakan Metode Stopword Removal dan Stemming,” Prosiding Konstelasi Ilmiah Mahasiswa Unissula (KIMU), pp. 58–70, 2019.
J. Pardede, and D. Darmawan, “Perbandingan Algoritma Stemming Porter, Sastrawi, Idris, Arifin dan Setiono pada Dokumen Teks Bahasa Indonesia”, JTIK (Jurnal Teknologi Informasi dan Ilmu Komputer), vol. 12, no. 1, 2025, doi: 10.25126/jtiik.2025128860.
E. Muningsih, “Kombinasi Metode K-Means Dan Decision Tree Dengan Perbandingan Kriteria Dan Split Data,” J. Teknoinfo, vol. 16, no. 1, p. 113, 2022, doi: 10.33365/jti.v16i1.1561.
E. Rasywir, R. Sinaga, and Y. Pratama, “Analisis dan Implementasi Diagnosis Penyakit Sawit dengan Metode Convolutional Neural Network (CNN),” Paradig. - J. Komput. dan Inform., vol. 22, no. 2, pp. 117–123, 2020, doi: 10.31294/p.v22i2.8907.
A. Hanifa, S. A. Fauzan, M. Hikal, and M. B. Ashfiya, “Perbandingan Metode LSTM dan GRU (RNN) untuk Klasifikasi Berita Palsu Berbahasa Indonesia,” Din. Rekayasa, vol. 17, no. 1, p. 33, 2021, doi: 10.20884/1.dr.2021.17.1.436.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Komparasi Kinerja LSTM dan CNN dalam Deteksi Spam Email Berbasis Deep learning
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2025 Maugy Al Kautsar, Galet Guntoro Setiaji, Ahmad Rifa'i
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International 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 (Refer to The Effect of Open Access).
