Hyperparameter Optimization Of IndoBERT Using Grid Search, Random Search, And Bayesian Optimization In Sentiment Analysis Of E-Government Application Reviews
DOI:
https://doi.org/10.52436/1.jutif.2025.6.5.4897Keywords:
Bayesian Optimization, E-Government, Grid Search, Hyperparameter, IndoBERT, Random SearchAbstract
User reviews on Google Play Store reflect satisfaction and expectations regarding digital services, including E-Government applications. This study aims to optimize IndoBERT performance in sentiment classification through fine-tuning and hyperparameter exploration using three methods: Grid Search, Random Search, and Bayesian Optimization. Experiments were conducted on Sinaga Mobile app reviews, evaluated using accuracy, precision, recall, F1-score, learning curve, and confusion matrix. The results show that Grid Search with a learning rate of 5e-5 and a batch size of 16 provides the best results, with an accuracy of 90.55%, precision of 91.16%, recall of 90.55%, and F1-score of 89.75%. The learning curve indicates stable training without overfitting. This study provides practical contributions as a guide for improving IndoBERT in Indonesian sentiment analysis and as a foundation for developing NLP-based review monitoring systems to enhance public digital services.
Downloads
References
R. Artikel, M. I. Amal, E. S. Rahmasita, E. Suryaputra, and N. A. Rakhmawati, “Analisis Klasifikasi Sentimen Terhadap Isu Kebocoran Data Kartu Identitas Ponsel di Twitter Sentiment Classification Analysis On Phone Identity Card Data Leaks Issues On Twitter,” vol. 8, no. September, pp. 645–660, 2022.
K. A. Pradani, L. H. Suadaa, J. Timur, and P. Korespondensi, “Automated Essay Scoring Menggunakan Semantic Textual Automated Essay Scoring Using Transformer-Based Semantic,” vol. 10, no. 6, pp. 1177–1184, 2023, doi: 10.25126/jtiik.2023107338.
G. Z. Nabiilah, S. Y. Prasetyo, Z. N. Izdihar, and A. S. Girsang, “ScienceDirect ScienceDirect 7th International Conference on Computer Science and Computational Intelligence 2022 BERT base model for toxic comment analysis on BERT base model for toxic comment analysis on Indonesian social media Indonesian social media,” Procedia Comput. Sci., vol. 216, no. 2022, pp. 714–721, 2023, doi: 10.1016/j.procs.2022.12.188.
J. Nasional, S. Informasi, E. Teks, E. Marthen, and I. Novita, “Optimasi RoBERTa dengan Hyperparameter Tuning untuk Deteksi,” vol. 03, pp. 240–248, 2024.
A. Simanjuntak, R. Lumbantoruan, K. Sianipar, R. Gultom, M. Simaremare, and S. Situmeang, “Studi dan Analisis Hyperparameter Tuning IndoBERT Dalam Pendeteksian Berita Palsu,” vol. 13, pp. 60–67, 2024.
K. S. Nugroho, A. Y. Sukmadewa, F. A. Bachtiar, and N. Yudistira, “BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews,” pp. 1–10, 2020.
X. Teng, L. Zhang, P. Gao, C. Yu, and S. Sun, “BERT-Driven stock price trend prediction utilizing tokenized stock data and multi-step optimization approach,” Appl. Soft Comput., vol. 170, no. December 2024, p. 112627, 2025, doi: 10.1016/j.asoc.2024.112627.
P. Nur et al., “Bijakaweb : Platform Berbasis Web Untuk Deteksi Hate Speech Bijakaweb : A Web-Based Platform For Detecting Hate Speech In,” vol. 11, no. 4, pp. 939–948, 2024, doi: 10.25126/jtiik.1148719.
A. Turchin, S. Masharsky, and M. Zitnik, “Informatics in Medicine Unlocked Comparison of BERT implementations for natural language processing of narrative medical documents,” Informatics Med. Unlocked, vol. 36, no. November 2022, p. 101139, 2023, doi: 10.1016/j.imu.2022.101139.
T. D. Purnomo, J. Sutopo, and A. History, “Comparison Of Pre-Trained Bert-Based Transformer Models For Regional,” vol. 3, no. 3, pp. 11–21, 2024.
K. Kunci, “The Indonesian Journal of Computer Science,” vol. 13, no. 5, pp. 8350–8359, 2024.
H. S. Anggraheni, M. J. Naufal, and N. Yudistira, “Deteksi Spam Berbahasa Indonesia Berbasis Teks Menggunakan Model Bert Text-Based Indonesian Spam Detection Using The Bert Model,” vol. 11, no. 6, pp. 1291–1301, 2024, doi: 10.25126/jtiik.2024118121.
R. I. Perwira and V. A. Permadi, “Domain-Specific Fine-Tuning of IndoBERT for Aspect- Based Sentiment Analysis in Indonesian Travel User- Generated Content,” vol. 11, no. 1, pp. 30–40, 2025.
A. Alamsyah and Y. Sagama, “Intelligent Systems with Applications Empowering Indonesian internet users : An approach to counter online toxicity and enhance digital well-being,” Intell. Syst. with Appl., vol. 22, no. August 2023, p. 200394, 2024, doi: 10.1016/j.iswa.2024.200394.
F. Baharuddin, “Fine-Tuning IndoBERT for Indonesian Exam Question Classification Based on Bloom ’ s Taxonomy,” vol. 9, no. 2, 2023.
I. Griha, T. Isa, and P. N. Sriwijaya, “Hyperparameter Tuning Epoch dalam Meningkatkan Akurasi Data Latih dan Data Validasi pada Citra Pengendara,” no. November 2022, 2023, doi: 10.36499/psnst.v12i1.6697.
M. Evtimova, “Hyperparameter Tuning for Address Validation using Optuna Applied for Address Validation 2 Related Work 3 Standards for Postal Address in France,” vol. 12, pp. 105–111, 2024, doi: 10.37394/232018.2024.12.10.
T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” 2020.
Z. A. Annisa, R. S. Perdana, P. P. Adikara, U. Brawijaya, and P. Korespondensi, “Kombinasi Intent Classification Dan Named Entity Recognition Pada Data Berbahasa Indonesia Dengan Metode Dual Intent And Combining Intent Classification And Named Entity Recognition On,” vol. 11, no. 5, pp. 1017–1024, 2024, doi: 10.25126/jtiik.2024117985.
M. N. Zaidan, Y. Sibaroni, and S. S. Prasetiyowati, “LEARNING RATE AND EPOCH OPTIMIZATION IN THE FINE-TUNING PROCESS FOR INDO BERT ’ S PERFORMANCE ON SENTIMENT ANALYSIS OF,” vol. 5, no. 5, pp. 1443–1450, 2024.
U. Khairani, V. Mutiawani, and H. Ahmadian, “Pengaruh Tahapan Preprocessing Terhadap Model Indobert Dan Indobertweet Untuk Mendeteksi Emosi Pada Komentar Akun Berita Instagram,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 4, pp. 887–894, 2024, doi: 10.25126/jtiik.1148315.
I. D. A. N. I. Pada, “Perbandingan Kinerja Pre-Trained Tokopedia Seller Center,” vol. 11, no. 2, pp. 13–20, 2024, doi: 10.30656/jsii.v11i2.9168.
B. Bischl et al., “Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 13, no. 2, pp. 1–43, 2023, doi: 10.1002/widm.1484.
R. Pramana, M. Jonathan, H. S. Yani, and R. Sutoyo, “A Comparison of BiLSTM, BERT, and Ensemble Method for Emotion Recognition on Indonesian Product Reviews,” Procedia Comput. Sci., vol. 245, no. C, pp. 399–408, 2024, doi: 10.1016/j.procs.2024.10.266.
R. Nugroho, N. Azka, W. Sayudha, and R. Graha, “Jurnal JTIK ( Jurnal Teknologi Informasi dan Komunikasi ) Analisis Sentimen Ulasan Aplikasi Mobile JKN di Google,” vol. 9, no. June, pp. 495–505, 2025.
L. Geni, E. Yulianti, and D. I. Sensuse, “Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models,” J. Ilm. Tek. Elektro Komput. dan Inform., vol. 9, no. 3, pp. 746–757, 2023, doi: 10.26555/jiteki.v9i3.26490.
P. Jeevallucas et al., "Analisis Sentimen Pengguna terhadap Akun X/Twitter Resmi ‘DANA’ dengan Algoritma IndoBERT," Jurnal Teknologi Informasi dan Komunikasi, vol. 8, no. 11, pp. 549–559, 2025.
C. J. L. Tobing, I. G. N. L. Wijayakusuma, L. Putu, I. Harini, and U. Udayana, “Detection of Political Hoax News Using Fine-Tuning IndoBERT,” vol. 9, no. 2, pp. 354–360, 2025.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Angga Iskoko, Imam Tahyudin, Purwadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
