Public Response on X to the Revocation of Indonesia’s 3-Kg LPG Retail Ban: A Support Vector Machine Study

Ni Nyoman Asti Sri Wahyuni; I Gede Iwan Sudipa; Ni Nyoman Ayu J.  Sastaparamitha; Ayu Gede  Willdahlia; I Gusti Ayu Agung Mas  Aristamy

doi:10.56705/ijodas.v6i3.349

Authors

Ni Nyoman Asti Sri Wahyuni Institut Bisnis dan Teknologi Indonesia, Denpasar, Indonesia
I Gede Iwan Sudipa Institut Bisnis dan Teknologi Indonesia, Denpasar, Indonesia
Ni Nyoman Ayu J. Sastaparamitha Institut Bisnis dan Teknologi Indonesia, Denpasar, Indonesia
Ayu Gede Willdahlia Institut Bisnis dan Teknologi Indonesia, Denpasar, Indonesia
I Gusti Ayu Agung Mas Aristamy Institut Bisnis dan Teknologi Indonesia, Denpasar, Indonesia

DOI:

https://doi.org/10.56705/ijodas.v6i3.349

Keywords:

Sentiment Analysis, Public Response, Government Policy, 3-Kilogram LPG, Support Vector Machine

Abstract

This study examines public responses on X to the 3-Kg LPG retail ban implemented on February 1, 2025, and revoked on February 4, 2025, which caused widespread shortages, long queues, and limited access, particularly for citizens living far from official distribution points. A total of 2,524 Indonesian-language tweets were collected via crawling and systematically processed through text cleaning, tokenization, normalization, stopwords removal, and stemming, followed by automatic labeling using the Indonesian Sentiment (InSet) Lexicon. After removing 229 neutral tweets, 1,405 tweets (61.2%) were classified as negative and 890 tweets (38.8%) as positive, with the study focusing on these two sentiment classes. Text features were extracted using TF-IDF, and classification was conducted using a linear-kernel Support Vector Machine (C = 0.1) with an 80:20 train-test split. The model achieved an overall accuracy of 84%, with precision, recall, and F1-score of 0.82, 0.94, and 0.88 for the negative class, and 0.87, 0.68, and 0.76 for the positive class. Results indicate that negative sentiment was dominated by criticism related to LPG shortages and insufficient policy communication, while positive sentiment reflected user relief over restored supply and hopes for fairer distribution in the future. These findings suggest that revoking the ban did not fully restore public perception, highlighting the necessity for more effective policy dissemination and stricter monitoring of 3-Kg LPG distribution. The study also emphasizes the importance of leveraging social media, particularly X, as a real-time source for monitoring public opinion and evaluating the effectiveness of energy distribution policies in Indonesia.

Downloads

Download data is not yet available.

References

[1] BPS, “Indikator Perumahan dan Kesehatan Lingkungan 2024 - Badan Pusat Statistik Indonesia,” bps.go.id/. Accessed: Jun. 12, 2025. [Online]. Available: https://www.bps.go.id/id/publication/2024/12/31/66a8541b654e6bc0f333cb4f/indikator-perumahan-dan-kesehatan-lingkungan-2024.html
[2] S. Barreto, R. Moura, J. Carvalho, A. Paes, and A. Plastino, “Sentiment analysis in tweets: an assessment study from classical to modern word representation models,” Data Min. Knowl. Discov., vol. 37, no. 1, pp. 318–380, 2023, doi: 10.1007/s10618-022-00853-0.
[3] A. Jaya, “Analisis Sentimen Pandangan Public Profesi PNS (Pegawai Negeri Sipil) dari Twiter menerapkan indonesian Roberta Base Sentiment Classifier,” Indones. J. Data Sci., vol. 4, no. 1, pp. 38–44, 2023, doi: 10.56705/ijodas.v4i1.66.
[4] Z. Zakaria, K. Kusrini, and D. Ariatmanto, “Sentiment Analysis to Measure Public Trust in the Government Due to the Increase in Fuel Prices Using Naive Bayes and Support Vector Machine,” Int. J. Artif. Intell. Robot., vol. 5, no. 2, pp. 54–62, 2023, doi: 10.25139/ijair.v5i2.7167.
[5] I. Amelia and F. M. Sarimole, “Analisis Sentimen Tanggapan Pengguna Media Sosial X Terhadap Program Beasiswa KIP-Kuliah dengan Menggunakan Algoritma Support Vector Machine ( SVM ),” vol. 5, no. 3, pp. 2994–3003, 2024.
[6] P. Arsi and R. Waluyo, “Analisis Sentimen Wacana Pemindahan Ibu Kota Indonesia Menggunakan Algoritma Support Vector Machine (SVM),” J. Teknol. Inf. dan Ilmu Komput., vol. 8, no. 1, p. 147, 2021, doi: 10.25126/jtiik.0813944.
[7] Y. Qi, “Construction of Online English Corpus Based on Web Crawler Technology,” Wirel. Commun. Mob. Comput., vol. 2022, 2022, doi: 10.1155/2022/7589727.
[8] M. A. Palomino and F. Aider, “Evaluating-the-Effectiveness-of-Text-PreProcessing-in-Sentiment-AnalysisApplied-Sciences-Switzerland.pdf,” Appl. Sci., vol. 12, p. 8765, 2022.
[9] R. R. Raja and H. Darwis, “A Comparative Study of Public Opinion on Indonesian Police : Examining Cases in the Aftermath of the Kanjuruhan Football Disaster,” Indones. J. Data Sci., vol. 6, no. 1, pp. 260–270, 2025.
[10] A. Tareque, H. H. Siddegowda, D. J. Frank, N. Lee, and R. Moieni, “Overview of Machine Learning Algorithms for Detecting Microaggression in Written Text,” Open J. Soc. Sci., vol. 12, no. 07, pp. 347–358, 2024, doi: 10.4236/jss.2024.127025.
[11] A. R. Lubis, Y. Y. Lase, D. A. Rahman, and D. Witarsyah, “Improving Spell Checker Performance for Bahasa Indonesia Using Text Preprocessing Techniques with Deep Learning Models,” Ing. des Syst. d’Information, vol. 28, no. 5, pp. 1335–1342, 2023, doi: 10.18280/isi.280522.
[12] D. Drašković and S. Milanović, “Aspect-based sentiment analysis of user-generated content from a microblogging platform,” J. Big Data, vol. 12, no. 1, 2025, doi: 10.1186/s40537-025-01244-0.
[13] J. Khan and S. Lee, “Article enhancement of text analysis using context-aware normalization of social media informal text,” Appl. Sci., vol. 11, no. 17, 2021, doi: 10.3390/app11178172.
[14] S. Sarica and J. Luo, “Stopwords in technical language processing,” PLoS One, vol. 16, no. 8 August, pp. 1–13, 2021, doi: 10.1371/journal.pone.0254937.
[15] N. A. Razmi, M. Z. Zamri, S. S. S. Ghazalli, and N. Seman, “Visualizing stemming techniques on online news articles text analytics,” Bull. Electr. Eng. Informatics, vol. 10, no. 1, pp. 365–365, 2021, doi: 10.11591/eei.v10i1.2504.
[16] F. Koto and G. Y. Rahmaningtyas, “Inset lexicon: Evaluation of a word list for Indonesian sentiment analysis in microblogs,” Proc. 2017 Int. Conf. Asian Lang. Process. IALP 2017, vol. 2018-Janua, no. December, pp. 391–394, 2017, doi: 10.1109/IALP.2017.8300625.
[17] H. Liu, X. Chen, and X. Liu, “A Study of the Application of Weight Distributing Method Combining Sentiment Dictionary and TF-IDF for Text Sentiment Analysis,” IEEE Access, vol. 10, pp. 32280–32289, 2022, doi: 10.1109/ACCESS.2022.3160172.
[18] Q. H. Nguyen et al., “Influence of data splitting on performance of machine learning models in prediction of shear strength of soil,” Math. Probl. Eng., vol. 2021, 2021, doi: 10.1155/2021/4832864.
[19] M. Sivakumar, S. Parthasarathy, and T. Padmapriya, “Trade-off between training and testing ratio in machine learning for medical image processing,” PeerJ Comput. Sci., vol. 10, pp. 1–17, 2024, doi: 10.7717/PEERJ-CS.2245.
[20] R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review,” Inf., vol. 15, no. 4, 2024, doi: 10.3390/info15040235.
[21] N. Amaya-Tejera, M. Gamarra, J. I. Vélez, and E. Zurek, “A distance-based kernel for classification via Support Vector Machines,” Front. Artif. Intell., vol. 7, 2024, doi: 10.3389/frai.2024.1287875.
[22] S. J. and D. K. U., “Comparison of Sentiment Analysis on Online Product Reviews Using Optimised RNN-LSTM with Support Vector Machine,” Webology, vol. 19, no. 1, pp. 3883–3898, 2022, doi: 10.14704/web/v19i1/web19256.
[23] A. Umair and E. Masciari, “Sentimental and spatial analysis of COVID-19 vaccines tweets,” J. Intell. Inf. Syst., vol. 60, no. 1, pp. 1–21, 2023, doi: 10.1007/s10844-022-00699-4.
[24] T. Malik et al., “Crowd Control, Planning, and Prediction Using Sentiment Analysis: An Alert System for City Authorities,” Appl. Sci., vol. 13, no. 3, 2023, doi: 10.3390/app13031592.
[25] D. Anggraini, I. Gamayanto, and S. Wibowo, “Comparing Decision Tree and Support Vector Machines in Hospital Satisfaction,” J. Appl. Informatics Comput., vol. 9, no. 2, pp. 364–372, 2025, doi: 10.30871/jaic.v9i2.9203.
[26] H. T. Duong and T. A. Nguyen-Thi, “A review: preprocessing techniques and data augmentation for sentiment analysis,” Comput. Soc. Networks, vol. 8, no. 1, pp. 1–16, 2021, doi: 10.1186/s40649-020-00080-x.
[27] P. Haryoko, A. Syukur, and N. Rijati, “Development of a Mental Health Classifier Using LSTM and Text Preprocessing Techniques,” Sci. J. Informatics, vol. 12, no. 1, pp. 77–86, 2025, doi: 10.15294/sji.v12i1.21216.