Performance Analysis of SVM and BERT in Predicting the Availability of Stunting Prevention Services in Indonesia

Bayu Anugerah Putra; Fitri Handayani; Yulia Fatma; Jhidan Daelvin Hendra

doi:10.30595/juita.v14i1.27950

Authors

Bayu Anugerah Putra Universitas Muhammadiyah Riau
Fitri Handayani Universitas Muhammadiyah Riau
Yulia Fatma Universitas Muhammadiyah Riau
Jhidan Daelvin Hendra Universitas Muhammadiyah Riau

DOI:

https://doi.org/10.30595/juita.v14i1.27950

Keywords:

Stunting; SVM; machine learning; BERT; stunting prevention.

Abstract

Stunting, defined as being too short for one's age with a Height-for-Age Z-score (HAZ) below –2 SD according to WHO, remains a serious public health problem in Indonesia. This study predicts the availability of stunting prevention services at the village level using machine learning. Data from 25,800 villages were categorized into Complete (9,245), Partial (13,609), and Not Available (2,946), showing class imbalance. Two algorithms were evaluated: Support Vector Machine (SVM) with TF-IDF and SMOTE for class balancing, and Bidirectional Encoder Representations from Transformers (BERT) using IndoBERT with class-weighted loss. Evaluation metrics included accuracy, precision, recall, F1-score, and computation time. Results show BERT achieved 92% accuracy with consistent performance across classes (cross-validation 91.55%, SD 0.0024), effectively capturing contextual meaning in narrative text. SVM reached 83% test accuracy with fast computation (±1 min 42 s) and remained robust for imbalanced data. Both models performed well, but minority-class recognition remains challenging. These findings highlight the complementary strengths of SVM and BERT, providing data-driven insights to support policy decisions and improve targeting of stunting prevention services at the village level.

Author Biographies

Bayu Anugerah Putra, Universitas Muhammadiyah Riau

Department of Informatics Engineering

Fitri Handayani, Universitas Muhammadiyah Riau

Department of Informatics Engineering

Yulia Fatma, Universitas Muhammadiyah Riau

Department of Informatics Engineering

Jhidan Daelvin Hendra, Universitas Muhammadiyah Riau

Department of Informatics Engineering

References

[1] A. Islamiyati, M. Nur, A. Salam, W. Z. A. W. Muhamad, and D. Auliyah, “Risk factor analysis for stunting incidence using sparse categorical principal component logistic regression,” MethodsX, vol. 14, p. 103186, 2025, doi: 10.1016/j.mex.2025.103186.

[2] Hijrawati, A. N. Usman, S. Syarif, V. Hadju, S. As’ad, and Y. S. Baso, “Use Of Technology For Monitoring The Development Of Nutritional Status 1000 HPK In Stunting Prevention In Indonesia,” Gac. Sanit., vol. 35, pp. S231–S234, 2021, doi: 10.1016/j.gaceta.2021.10.028.

[3] A. K. Manggala, K. W. M. Kenwa, M. M. L. Kenwa, A. A. G. D. P. J. Sakti, and A. A. S. Sawitri, “Risk Factors of Stunting in Children Aged 24-59 Months,” Paediatr. Indones., vol. 58, no. 5, hal. 205–212, 2018, doi: 10.14238/pi58.5.2018.205-12.

[4] Y. Haskas, “Overview of Stunting in Indonesia: Literatur Review,” J. Ilm. Kesehat. Diagnosis, vol. 15, no. 2, pp. 154–157, 2020.

[5] WHO, Global nutrition targets 2025: stunting policy brief (WHO/NMH/NHD/14.3). Geneva: World Health Organization, 2014.

[6] UNICEF, Nutrition, For Every Child: UNICEF Nutrition Strategy 2020–2030. New York: United Nations Children’s Fund, 2020.

[7] L. Nurcahyani, D. Widiyastuti, W. Estuti, A. T. Iman, Y. Fitrianingsih, and F. Hafid, “Design of Stunting Prevention Education Media Package Based on Technology and Local Wisdom,” Amerta Nutr., vol. 8, no. 2SP, pp. 9–14, 2024, doi: 10.20473/amnt.v8i2SP.2024.9-14.

[8] Tumaji, A. D. Laksono, and H. D. Kusumawardani, “Children’s Characteristics as the Predictors of Stunting among Children Under 2 Years in East Nusa Tenggara in Indonesia,” Indian J. Community Med., vol. 50, no. 1, pp. 162–168, 2025, doi: 10.4103/ijcm.ijcm_384_23.

[9] I. Kareem, S. F. Ali, M. Bilal, and M. S. Hanif, “Exploiting The Features Of Deep Residual Network With SVM Classifier For Human Posture Recognition,” PLoS One, vol. 19, no. 12, p. e0314959, 2024, doi: 10.1371/journal.pone.0314959.

[10] N. Hasdyna, R. K. Dinata, Rahmi, and T. I. Fajri, “Hybrid Machine Learning for Stunting Prevalence: A Novel Comprehensive Approach to Its Classification, Prediction, and Clustering Optimization in Aceh, Indonesia,” Informatics, vol. 11, no. 4, p. 89, 2024, doi: 10.3390/informatics11040089.

[11] S. Y. Andriyani, M. S. Lydia, and S. Efendi, “Optimization of Support Vector Machine Algorithm Using Stunting Data Classification,” Prism. Sains J. Pengkaj. Ilmu dan Pembelajaran Mat. dan IPA IKIP Mataram, vol. 11, no. 1, p. 164, 2023, doi: 10.33394/j-ps.v11i1.6619.

[12] I. Rahmi, M. Susanti, H. Yozza, and F. Wulandari, “Classification Of Stunting In Children Under Five Years In Padang City Using Support Vector Machine,” BAREKENG J. Ilmu Mat. dan Terap., vol. 16, no. 3, pp. 771–778, 2022, doi: 10.30598/barekengvol16iss3pp771-778.

[13] S. W. Lee, J. H. Kwon, D. Kim, and E. J. Kim, “Research Category Classification Of Scientific Articles On Human Health Risks Of Electromagnetic Fields Using Pre-Trained BERT,” ICT Express, vol. 10, no. 2, pp. 336–341, 2024, doi: 10.1016/j.icte.2023.08.006.

[14] D. Suhartono, I. F. Saputra, A. R. Pratama, and G. Nathaniel, “Psychological Stress Detection Using Transformer-Based Models,” ComTech Comput. Math. Eng. Appl., vol. 15, no. 1, pp. 65–71, 2024, doi: 10.21512/comtech.v15i1.11105.

[15] W. Lu, J. Jiang, Y. Shi, X. Zhong, J. Gun, L. Huangfu, and M. Gong, “Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition,” Front. Neurosci., vol. 17, pp. 1-19, 2023, doi: 10.3389/fnins.2023.1259652.

[16] A. Muzakir, K. Adi, and R. Kusumaningrum, Application of Machine Learning and Deep Learning Concepts. Semarang: UNDIP Press, 2024.

[17] A. Tholib, Reference Book on Implementing Web-Based Machine Learning Algorithms with the Streamlit Framework, 1 ed. Probolinggo: Pustaka Nurja, 2023. doi: 10.1128/AAC.03728-14.

[18] R. F. Putra, I. R. Mukhlis, A. I. Datya, S. J. Pipin, F. Reba, M. Alhusaini, S. A. Mandowen, N. N. L. E. Zain, and L. Judijanto, Machine Learning Algorithms (Fundamentals, Techniques, and Applications), 1 ed. Jambi: PT. Sonpedia Publishing Indonesia, 2024.

[19] A. R. Hanum, I. A. Zetha, J. N. Fajrina, R. A. Wulandari, S. C. Putri, S. P. Andina, and N. Yudistira, “Performance Analysis of Text Classification Algorithms in Detecting Fake News,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 3, pp. 537–546, 2024, doi: 10.25126/jtiik.938093.