Deep Learning Evaluation for Interactive Dashboard-Base Mail Classification
Evaluasi Pembelajaran Mendalam untuk Klasifikasi Email Berbasis Dasbor Interaktif
DOI:
https://doi.org/10.25134/ilkom.v20i1.546Keywords:
mail archive classification, deep learning, interactive dashboard, CNN, clusteringAbstract
The management of incoming mail archives at a large national logistics company in Indonesia generates a large volume of unstructured textual data, making manual classification inefficient and error-prone. This study evaluates the performance of deep learning models for administrative mail archives classification using data collected between 2023 and 2025. Three models are examined, namely Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Convolutional Neural Network (CNN). Model performance is evaluated using accuracy, precision, recall, F1-score, and confusion matrix metrics. Experimental results indicate that CNN achieves the highest accuracy of 85.82%, outperforming LSTM and Bi-LSTM models. This superior performance is attributed to CNN’s ability to capture local textual patterns through convolution operations, which are well-suited to the structured and repetitive language characteristics of official correspondence. To support practical interpretation, an interactive dashboard is implemented as a visualization tool for model evaluation results, classification outcomes, and clustering analysis. These findings demonstrate that deep learning-based approaches integrated with visual analytics can significantly improve the efficiency and accuracy of unstructured mail archive management
Downloads
References
[1] F. Nikmah, D. J. Pribadi, E. A. Sukma, E. Suwarni, and I. Azmi, “Decision Support System For Handling Incoming And Outgoing Mail: To Facilitate Archives Retrieval,” Int. J. Acad. Res. Reflect., vol. 10, no. 3, pp. 53–61, 2022, [Online]. Available: www.idpublications.org
[2] J. F. Indey and S. Supangat, “Implementasi Algoritma Naïve Bayes Dalam Sistem Pengarsipan Surat Berbasis Ai Di Gpi Papua Klasis Mimika Papua Tengah,” J. Ilm. Inform., vol. 12, no. 2, pp. 102–113, 2024, doi: 10.33884/jif.v12i02.9087.
[3] F. R. Gerung, G. D. P. Maramis, and E. R. S. Moningkey, “Penerapan Algoritma Naive Bayes pada Arsip Surat,” Remik Ris. dan E-Jurnal Manaj. Inform. Komput., vol. 9, no. 2, pp. 676–690, 2025, doi: 10.33395/remik.v9i2.14786.
[4] R. A. Krisdiawan, “Implementasi Model Pengembangan Sistem GDLC dan Algoritma Linear Congruential Generator Pada Game Puzzle,” Nuansa Inform., vol. 12, no. 2, pp. 1–9, 2018, doi: 10.25134/nuansa.v12i2.1634.
[5] G. Mujtaba, L. Shuib, R. G. Raj, N. Majeed, and M. A. Al-Garadi, “Email Classification Research Trends: Review and Open Issues,” IEEE Access, vol. 5, pp. 9044–9064, 2017, doi: 10.1109/ACCESS.2017.2702187.
[6] Y. Kim, “Convolutional neural networks for sentence classification,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 1746–1751. doi: 10.3115/v1/d14-1181.
[7] R. A. Pakpahan and D. A. Utami, “Pengelolaan Arsip Surat Masuk Di Dinas Energi Dan Sumber Daya Mineral Provinsi Jawa Timur Melalui Aplikasi Tata Naskah Dinas Elektronik (TNDE),” J. Inov. Negara dan Terap., vol. 4, no. 1, pp. 211–222, 2025, [Online]. Available: https://journal.unesa.ac.id/index.php/innovant/article/download/38747/12867/125823#:~:text=Uraian diatas dapat disimpulkan bahwa,elektronik dengan proses penciptaan dan
[8] D. Z. Robert, A. B. Setiawan, and D. W. Widodo, “Implementasi metode support vector machine untuk klasifikasi otomatis pengaduan publik di Kabupaten Trenggalek,” Inotek J. Inov. Teknol., vol. 9, p. 1617, 2025.
[9] S. Pandey, A. Taralekar, R. Yadav, S. Deshmukh, and P. S. Suryavanshi, “E-mail Spam Detection and Classification using SVM,” Int. J. Comput. Sci. Inf. Technol., vol. 10, no. 1, pp. 6–8, 2020, [Online]. Available: http://www.ijcsit.com
[10] I. Kasim and Sahibu, “Klasifikasi Surat Digital Menggunakan Algoritma Naïve Bayes,” J. IT Media Inf. IT STMIK Handayani, vol. 13, no. 2, pp. 57–62, 2020.
[11] C. Magnolia, A. Nurhopipah, and B. A. Kusuma, “Penanganan Imbalanced Dataset untuk Klasifikasi Komentar Program Kampus Merdeka Pada Aplikasi Twitter,” Edu Komputika J., vol. 9, no. 2, pp. 105–113, 2022, doi: 10.15294/edukomputika.v9i2.61854.
[12] W. N. Ibrahem Al-Obaydy, H. A. Hashim, Y. AbdulKhaleq Najm, and A. A. Jalal, “Document classification using term frequency-inverse document frequency and K-means clustering,” Indones. J. Electr. Eng. Comput. Sci., vol. 27, no. 3, pp. 1517–1524, 2022, doi: 10.11591/ijeecs.v27.i3.pp1517-1524.
[13] A. Liani, “Analisis Perbandingan Kernel Algoritma Support Vector Machine dalam Mengklasifikasikan Skripsi Teknik Informatika berdasarkan Abstrak,” JOINS (Journal Inf. Syst., vol. 5, no. 2, pp. 240–249, 2020, doi: 10.33633/joins.v5i2.3715.
[14] J. and others MacQueen, “Some methods for classification and analysis of multivariate observations,” in Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1967, pp. 281–297.
[15] F. Martinez-Plumed et al., “CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 8, pp. 3048–3061, 2021, doi: 10.1109/TKDE.2019.2962680.
[16] M. R. Givari, M. R. Sulaeman, and Y. Umaidah, “Perbandingan Algoritma SVM, Random Forest Dan XGBoost Untuk Penentuan Persetujuan Pengajuan Kredit,” Nuansa Inform., vol. 16, no. 1, pp. 141–149, 2022, doi: 10.25134/nuansa.v16i1.5406.
[17] M. A. Senubekti and L. A. Puspita Dewi, “Prinsip Klasifikasi Dan Data Mining Dengan Algoritma C4.5,” Nuansa Inform., vol. 16, no. 2, pp. 87–93, 2022, doi: 10.25134/nuansa.v16i2.5834.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ruth Diana Purnamasari, Nisa Hanum
This work is licensed under a Creative Commons Attribution 4.0 International License.
