Penerapan Explainable AI LIME pada Klasifikasi Sentimen Isu IKN, PPN, dan MBG Menggunakan IndoBERTweet
DOI:
https://doi.org/10.24252/shift.v6i1.236Keywords:
Explainable Artificial Intelligence, IndoBERTweet, LIME, Social Media, SentimentAbstract
Social media, particularly the X platform (formerly Twitter), has become a primary space for the public to express their opinions on public policy. This study aimed to classify public sentiment towards three strategic issues in Indonesia: the relocation of the national capital (IKN), the 11% VAT increase policy, and the Free Nutritious Meals (MBG) program by applying the IndoBERTweet model combined with a LIME-based Explainable Artificial Intelligence (XAI) approach. A dataset of 2,845 tweets was obtained through scraping using relevant keywords. The sentiment distribution in the data reveals a dominance of negative sentiment, with 1,575 tweets, followed by positive sentiment, with 1,005 tweets, and neutral sentiment, with 265 tweets. The IndoBERTweet model, trained for three epochs, produced an accuracy of 89% and an average macro F1-score of 0.78. The highest performance was achieved in both the positive and negative classes, with an F1-score of 0.92, while neutral sentiment remained challenging, with an F1-score of 0.49. To improve prediction transparency, the LIME method was employed and successfully displayed consistent visualizations that identified the dominant words influencing the classification. This study demonstrates the potential application of explainable Indonesian language transformer models for sentiment analysis of national policies in the digital realm.
Downloads
References
[1] M. Wankhade, A. C. S. Rao, and C. Kulkarni, “A survey on sentiment analysis methods, ap-plications, and challenges,” Artif Intell Rev, vol. 55, no. 7, pp. 5731–5780, Oct. 2022, doi: 10.1007/s10462-022-10144-1.
[2] A. S. Hanin and M. Maryam, “Sentiment Analysis of Twitter Towards the Free Lunch Pro-gram Using the C4.5 Algorithm,” International Journal of Advances in Data and Infor-mation Systems, vol. 6, no. 1, pp. 31–45, Apr. 2025, doi: 10.59395/ijadis.v6i1.1357.
[3] C. Juditha, “The Phenomenon of ‘Indonesia Gelap’ on Social Media: Sentiment Analysis and Public Opinion Polarization,” Jurnal Komunikasi, vol. 17, no. 1, pp. 157–170, Jul. 2025, doi: 10.24912/jk.v17i1.33846.
[4] G. Z. Nabiilah, I. N. Alam, E. S. Purwanto, and M. F. Hidayat, “Indonesian multilabel classi-fication using IndoBERT embedding and MBERT classification,” International Journal of Electrical and Computer Engineering, vol. 14, no. 1, pp. 1071–1078, Feb. 2024, doi: 10.11591/ijece.v14i1.pp1071-1078.
[5] M. N. P. Abadi et al., “Unraveling Future Trends in Free School Lunch and Nutrition: Glob-al Insights for Indonesia from Bibliometric Approach and Critical Review,” Sep. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/nu17172777.
[6] I. Hermansyah and M. S. Hasibuan, “Sentiment Analysis of Free Nutritious Meal Pro-gramme on Social Media X using Linear Regression and Random Forest Algorithms,” PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic, vol. 13, no. 1, pp. 55–68, Mar. 2025, doi: 10.33558/piksel.v13i1.10633.
[7] M. Farhan Saleh and R. Imanda, “Public Sentiment Analysis of the Free Meal Program: A Comparison of Naive Bayes and Support Vector Machine Methods on the Twitter (X) Social Media Platform,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[8] A. Elbasiony, I. M. El-Hasnony, and S. Abdelrazek, “XAI-Based Sentiment Analysis Using Ma-chine Learning Approaches,” Mansoura Journal for Computer and Information Sciences, vol. 19, no. 1, pp. 23–42, Dec. 2024, doi: 10.21608/mjcis.2024.275844.1002.
[9] Devlin, Jacob, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. "Bert: Pre-training of deep bidirectional transformers for language understanding." In Proceedings of the 2019 conference of the North American chapter of the association for computational linguis-tics: human language technologies, volume 1 (long and short papers), pp. 4171-4186. 2019.
[10] T. Dwi Purnomo and J. Sutopo, “Comparison Of Pre-Trained Bert-Based Transformer Mod-els For Regional Language Text Sentiment Analysis In Indonesia” no. 3, pp. 11–21, 2024, doi: 10.56127/ijst.v3i3.1.
[11] F. Koto, J. H. Lau, and T. Baldwin, “IndoBERTweet: A Pretrained Language Model for Indo-nesian Twitter with Effective Domain-Specific Vocabulary Initialization,” Sep. 2021, [Online]. Available: http://arxiv.org/abs/2109.04607
[12] H. Jayadianti, W. Kaswidjanti, A. T. Utomo, S. Saifullah, F. A. Dwiyanto, and R. Drezewski, “Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN,” ILKOM Jurnal Ilmiah, vol. 14, no. 3, pp. 348–354, Dec. 2022, doi: 10.33096/ilkom.v14i3.1505.348-354.
[13] Dhendra and V. Gayuh Utomo, “Benchmarking IndoBERT and Transformer Models for Sen-timent Classification on Indonesian E-Government Service Reviews,” Jurnal Transformat-ika, vol. 23, no. 1, pp. 86–95, Jul. 2025, doi: 10.26623/transformatika.v23i1.12095.
[14] N. Fauziah, “Analisis Sentimen Publik Terhadap Kenaikan Tarif PPN di Indonesia dengan Pendekatan VADER,” Jurnal Akuntansi dan Keuangan, vol. 12, no. 2, p. 228, Sep. 2024, doi: 10.29103/jak.v12i2.16796.
[15] A. Sawant, “A Comparative Study of SHAP and LIME: Interpreting Black-Box Machine Learning Models,” International Journal Of Scientific Research In Engineering And Man-agement, vol. 09, no. 07, pp. 1–9, Jul. 2025, doi: 10.55041/IJSREM51586.
[16] D. Gunning, M. Stefik, J. Choi, T. Miller, S. Stumpf, and G. Z. Yang, “XAI-Explainable artifi-cial intelligence,” Sci Robot, vol. 4, no. 37, Dec. 2019, doi: 10.1126/scirobotics.aay7120.
[17] J. Dieber and S. Kirrane, “Why model why? Assessing the strengths and limitations of LIME,” Nov. 2020, [Online]. Available: http://arxiv.org/abs/2012.00093
[18] M. Danilevsky, K. Qian, R. Aharonov, Y. Katsis, B. Kawas, and P. Sen, “A Survey of the State of Explainable AI for Natural Language Processing,” Oct. 2020, doi: 10.18653/v1/2020.aacl-main.46.
[19] K. Kenyon-Dean et al., “Sentiment Analysis: It’s Complicated! 1.” [Online]. Available: https://github.com/networkdynamics/
[20] I. Sa’diyah, A. T. Aviolla Terza, C. C. B. Lima, M. R. M. Ariefean, and I. Athallah, “Sentiment Analysis of Netizen’s Comments on YouTube about IKN (Capital City) Development in In-donesia,” GHANCARAN: Jurnal Pendidikan Bahasa dan Sastra Indonesia, vol. 6, no. 2, Jan. 2025, doi: 10.19105/ghancaran.v6i2.15432.
[21] M. R. Manoppo et al., “Analisis Sentimen Publik Di Media Sosial Terhadap Kenaikan PPN 12% Di Indonesia Menggunakan Indobert” Jurnal Kecerdasan Buatan dan Teknologi In-formasi, vol. 4, no. 2, pp. 152–163, May 2025, doi: 10.69916/jkbti.v4i2.322.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Luthfi Delvian, Esa Firmansyah, Beben Sutara
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
