KLASIFIKASI SURAT MASUK DI KANTOR PENGADILAN MILITER III-15 KUPANG MENGGUNAKAN (LSTM) LONG SHORT TERM-MEMORY

Asmawati  Tuto; Sumarlin; Yohanis Malelak

doi:10.46880/mtk.v12i2.5924

Authors

Asmawati Tuto STIKOM Uyelindo Kupang
Sumarlin STIKOM Uyelindo Kupang
Yohanis Malelak STIKOM Uyelindo Kupang

DOI:

https://doi.org/10.46880/mtk.v12i2.5924

Keywords:

LSTM, Text Classification, Incoming Letters, Natural Language Processing, K-Fold Cross Validation, Military Court

Abstract

The increasing volume of incoming correspondence at the Kupang Military Court III-15 Office has made the conventional letter classification process complex and time-consuming. Purpose: this study aims to develop an incoming letter classification system that categorizes letters into four classes (regular letters, circulars, decrees, and orders) using the Long Short-Term Memory (LSTM) method; the main contribution of this study is the application of LSTM to a local military-court correspondence dataset that has not been widely studied, together with a replicable preprocessing pipeline and K-Fold evaluation protocol, providing practical implications for accelerating correspondence administration in military judicial offices. Methods: the dataset consists of 500 incoming letter records in Excel format that underwent a preprocessing stage including cleaning, case folding, normalization, stopword removal, stemming, tokenizing, encoding, and padding, and was then divided into 80% training data and 20% testing data, evaluated using 5-Fold Cross Validation with accuracy, precision, recall, and F1-score as performance metrics. Results: the average model performance results were Accuracy 42.04%, Precision 42.39%, Recall 42.04%, and F1-Score 39.93%, with the highest accuracy obtained in Fold 2 (56.44%) and the lowest in Fold 5 (32.00%), while the model's main difficulty lay in distinguishing between the Circular and Decree categories, which share similar text patterns. Conclusion: the LSTM method is capable of recognizing textual patterns in letters and performing classification; however, its performance remains variable and relatively low on this dataset, so the developed system has the potential to improve the efficiency of incoming letter management at the Kupang Military Court III-15 Office, although further optimization is still needed before independent deployment.

References

H. Kisma and Yohanis, “Pengelolaan Surat Masuk Dan Surat Keluar di Sekretariat Daerah Kabupaten Solok Selatan,” J. Adm. Publik dan Pemerintah., vol. 3, no. 1, pp. 17–23, 2024, doi: 10.55850/simbol.v3i1.99.

A. Fungsi and A. Pada, “Long Short Term Memory Untuk Klasifikasi Teks Oleh : Daniel Royhan Suhega Harahap Fakultas Teknik Diajukan sebagai Salah Satu Syarat untuk Memperoleh Gelar Sarjana di Fakultas Teknik Universitas Medan Area Daniel Royhan Suhega Harahap Fakultas Teknik,” 2024.

M. Al Fayed, U. Pembangunan, and P. Budi, “Perancangan Sistem Informasi Administrasi Surat Masuk dan Surat Keluar Pada Dinas Kominfo Serdang Bedagai,” J. Minfo Polgan, vol. 13, pp. 2049–2055, 2024.

I. Pratiwi, “Implementasi Algoritma Left Corner Parsing Dalam Pencarian Surat Pada Arsip Surat Masuk dan Surat Keluar,” Bull. Data Sci., vol. 1, no. 3, pp. 99–102, 2022, doi: 10.47065/bulletinds.v1i3.2147.

Rosalina Kambia and Megananda Cahya Dewi, “Prosedur Penanganan Surat Masuk Dan Surat Keluar Di Kantor Pos Solo 57100 Studi Kasus Pada Penanganan Surat Pt Pos Yang Ada Di Kota Solo,” J. Ilm. Ekon. Dan Manaj., vol. 2, no. 9, pp. 437–447, 2024, doi: 10.61722/jiem.v2i9.2564.

R. Amalia, N. Suarna, I. Ali, and D. I. Efendi, “Implementasi Algoritma K-Means Dalam Optimalisasi Pengelompokan Surat Masuk Di Pg. Sindanglaut,” J. Inform. dan Tek. Elektro Terap., vol. 13, no. 1, 2025, doi: 10.23960/jitet.v13i1.5876.

D. C. Arsiah and D. Anggita, “Pengelolaan Surat Menyurat Pada Bidang Peerdagangan Luar NegeriDinas Perindustrian Dan Perdagangan Kota Medan,” J. Pengabdi. dan Pemberdaya. Masy., vol. 1, no. 2, pp. 70–78, 2024.

M. Rizky Asyari and S. Ramadhani, “Sistem Informasi Arsip Surat Menyurat,” J. Teknol. dan Inf. Bisnis, vol. 3, no. 1, pp. 31–2021, 2021, [Online]. Available: https://doi.org/10.47233/jteksis.v3i1.172

N. A. Ramadhani and H. A. Rosyid, “Review: Algoritma Data Mining untuk Klasifikasi Data,” J. Inov. Teknol. dan Edukasi Tek., vol. 2, no. 12, pp. 550–556, 2022, doi: 10.17977/um068v2i122022p550-556.

K. N. Nababan, “Penerapan Metode K-Means Dalam Menentukan Klasifikasi Produk Pembelian Pelanggan,” BEES Bull. Electr. Electron. Eng., vol. 3, no. 2, pp. 81–97, 2022, doi: 10.47065/bees.v3i2.1129.

D. Azlil Huriah and N. Dienwati Nuris, “Klasifikasi Penerima Bantuan Sosial Umkm Menggunakan Algoritma Naïve Bayes,” JATI (Jurnal Mhs. Tek. Inform., vol. 7, no. 1, pp. 360–365, 2023, doi: 10.36040/jati.v7i1.6300.

P. A. M. Z. R.W.P.P.Zer and I. Gunawan, “Penerapan Data Mining Naïve Bayes Dalam Klasifikasi Kepuasan Mahasiswa Berlangganan WiFi Indihome,” J. Media Inform., vol. 3, no. 2, pp. 112–118, 2022, doi: 10.55338/jumin.v3i2.488.

Jatnika Fahmi Idris, Rafid Ramadhani, and Muhammad Malik Mutoffar, “Klasifikasi Penyakit Kanker Paru Menggunakan Perbandingan Algoritma Machine Learning,” J. Media Akad., vol. 2, no. 2, 2024, doi: 10.62281/v2i2.145.

F. Setiawan, “Klasifikasi Tingkat Urgensi Pengaduan Masyarakat Menggunakan Long Short-Term Memory ( Lstm ) ( Studi Kasus : Website Lapak Aduan Banyumas ),” vol. 12, no. 4, pp. 6820–6827, 2025.

F. N. Fajri and S. Syaiful, “Klasifikasi Nama Paket Pengadaan Menggunakan Long Short-Term Memory (LSTM) Pada Data Pengadaan,” Build. Informatics, Technol. Sci., vol. 4, no. 3, pp. 1625–1633, 2022, doi: 10.47065/bits.v4i3.2635.

A. I. Pradana and V. Atina, “Teknik K-Fold Cross Validation untuk Mengevaluasi Kinerja Mahasiswa,” pp. 239–248, 2024, doi: 10.33364/algoritma/v.21-1.1618.

M. Anjas, “Optimization of Classification Algorithms Performance with k-Fold Cross Validation,” no. 2, 2024.

I. Triyadi, B. Prasetiyo, and T. L. Nikmah, “News text classification using Long-Term Short Memory (LSTM) algorithm,” J. Soft Comput. Explor., vol. 4, no. 2, pp. 79–86, 2023.

A. Glenn, P. LaCasse, and B. Cox, “Emotion classification of Indonesian Tweets using Bidirectional LSTM,” Neural Comput. Appl., vol. 35, no. 13, pp. 9567–9578, 2023, doi: 10.1007/s00521-022-08186-1.

M. Liang and T. Niu, “Research on Text Classification Techniques Based on Improved TF-IDF Algorithm and LSTM Inputs,” Procedia Comput. Sci., vol. 208, pp. 460–470, 2022, doi: 10.1016/j.procs.2022.10.064.

E. D. Pratama, “Implementasi Model Long-Short Term Memory (LSTM) pada Klasifikasi Teks Data SMS Spam Berbahasa Indonesia,” J. Mach. Learn. Comput. Intell., vol. 1, no. 2, 2022, doi: 10.26740/vol1iss2y2022id12.

Y. Sagama and A. Alamsyah, “Multi-label Classification of Indonesian Online Toxicity Using BERT and RoBERTa,” in Proc. IAICT, 2023, doi: 10.1109/IAICT59002.2023.10205892.