Analisis Sentimen dan Distorsi Kognitif Konflik Anggaran Pendidikan dengan Makan Bergizi Gratis
DOI:
https://doi.org/10.35889/jutisi.v15i4.3924Abstract
The budget allocation conflict of the Free Nutritious Meal (MBG) program amounting to Rp223.5 trillion within the 2026 education budget has triggered opinion polarization and collective thinking bias on social media X. This study aims to analyze public sentiment distribution, identify dominant cognitive distortions, and test the statistical correlation between them. The methodology employs a two-layer parallel NLP pipeline utilizing the IndoBERTweet model for sentiment classification and the IndoBERT-base model for multilabel cognitive distortion detection across 2,000 tweets. Evaluation results show that the sentiment model achieves 83.25% accuracy, while the cognitive distortion detection reaches a subset accuracy of 83.75%, with Mental Filter being the most dominant type (8.2%). Fisher's Exact test proves a significant association ( < 0.05) between negative sentiment and the occurrence of Mental Filter and Catastrophizing. In conclusion, this hybrid approach effectively maps public collective thinking biases toward public policy dynamics.
Keywords: Sentiment Analysis; Cognitive Distortion; Free Nutritious Meal; IndoBERTweet; Fleiss' Kappa
Abstrak
Konflik alokasi anggaran program Makan Bergizi Gratis (MBG) sebesar Rp223,5 triliun dalam anggaran pendidikan APBN 2026 memicu polarisasi opini dan bias berpikir kolektif di media sosial X. Penelitian ini bertujuan menganalisis distribusi sentimen publik, mengidentifikasi distorsi kognitif dominan, serta menguji korelasi statistik di antara keduanya. Metodologi yang digunakan adalah pipeline NLP dua lapis paralel berbasis model IndoBERTweet untuk klasifikasi sentimen dan IndoBERT-base untuk deteksi distorsi kognitif multi-label terhadap 2.000 tweet. Hasil evaluasi menunjukkan model sentimen mencapai akurasi 83,25%, sedangkan deteksi distorsi kognitif meraih subset accuracy 83,75% dengan Mental Filter sebagai tipe paling dominan (8,2%). Uji Fisher's Exact membuktikan adanya hubungan signifikan ( < 0,05) antara sentimen negatif dengan kemunculan distorsi kognitif Mental Filter dan Catastrophizing. Simpulannya, pendekatan hybrid ini efektif dalam memetakan bias berpikir kolektif masyarakat terhadap dinamika kebijakan publik.
Kata Kunci: Analisis Sentimen; Distorsi Kognitif; Makan Bergizi Gratis; IndoBERTweet; Fleiss' Kappa
References
[1] “UU 17 TAHUN 2025 | Anggaran Pendapatan dan Belanja Negara Tahun Anggaran 2026.” Accessed: Jul. 12, 2026. [Online]. Available: https://djpb.kemenkeu.go.id/kppn/jakarta3/id/download/peraturan-terbaru/3051-uu-17-tahun-2025-anggaran-pendapatan-dan-belanja-negara-tahun-anggaran-2026.html
[2] “Direktorat Jenderal Perimbangan Keuangan | Peraturan Presiden Nomor 118 Tahun 2025 tentang Rincian Anggaran Pendapatan dan Belanja Negara Tahun Anggaran 2026.” Accessed: Jul. 12, 2026. [Online]. Available: https://djpk.kemenkeu.go.id/?p=72421
[3] “Perpres No. 115 Tahun 2025.” Accessed: Jul. 12, 2026. [Online]. Available: https://peraturan.bpk.go.id/Details/343430/perpres-no-115-tahun-2025
[4] “Permohonan Pengujian Undang-Undang Nomor 17 Tahun 2025 tentang APBN Tahun Anggaran 2026 Terhadap UUD 1945 Perkara No. 40, 52, dan 55/PUU-XXIV/2026.” Accessed: Jul. 12, 2026. [Online]. Available: https://tracking.mkri.id/index.php?page=web.TrackPerkara&id=52/PUU-XXIV/2026
[5] P. H. Nehe, S. S. Berutu, and H. Budiati, “Analisis Sentimen Opini Masyarakat Terhadap Presiden Jokowi Sebelum Dan Sesudah Pilpres 2024 Menggunakan Metode Naive Bayes Classification,” Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi, vol. 13, no. 1, p. 451, Apr. 2024, doi: 10.35889/jutisi.v13i1.1841.
[6] K. Syasyila, L. L. Gin, H. Abdullah Mohd. Nor, and M. R. Kamaluddin, “The role of cognitive distortion in criminal behavior: a systematic literature review,” BMC Psychol., vol. 12, no. 1, p. 741, Dec. 2024, doi: 10.1186/s40359-024-02228-0.
[7] Beck and Judith S, “Cognitive Behavior Therapy: Basics and Beyond (Third Edition),” New York, 2021.
[8] D. A. Sulistyo and E. Setiadi, “Analisis Sentimen Kebijakan Makan Bergizi Gratis Menggunakan IndoBERT dan Machine Learning,” JURNAL FASILKOM, vol. 15, no. 3, pp. 507–513, Dec. 2025, doi: 10.37859/jf.v15i3.10546.
[9] A. Z. Muhabbab, B. Bunyamin, and H. Hasmawati, “Sentiment Analysis of Indonesia’s Free Nutritious Meal Program on Platform X (Formerly Twitter) Using IndoBERT,” ZERO: Jurnal Sains, Matematika dan Terapan, vol. 9, no. 3, p. 884, Dec. 2025, doi: 10.30829/zero.v9i3.27629.
[10] A. P. Arunia, R. R. Sani, I. N. Dewi, and M. T. Sulistyono, “Exploring Public Opinion on the ‘Makan Bergizi Gratis’ Program on X: A Comparative Analysis of IndoBERT-Large and NusaBERT-Large Models,” Journal of Applied Informatics and Computing, vol. 10, no. 1, pp. 856–864, Feb. 2026, doi: 10.30871/jaic.v10i1.11757.
[11] S. Shreevastava and P. Foltz, “Detecting Cognitive Distortions from Patient-Therapist Interactions,” in Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access, Stroudsburg, PA, USA: Association for Computational Linguistics, 2021, pp. 151–158. doi: 10.18653/v1/2021.clpsych-1.17.
[12] Z. Chen, Y. Lu, and W. Wang, “Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting,” in Findings of the Association for Computational Linguistics: EMNLP 2023, Stroudsburg, PA, USA: Association for Computational Linguistics, 2023, pp. 4295–4304. doi: 10.18653/v1/2023.findings-emnlp.284.
[13] S. Lin, Y. Wang, J. Dong, and S. Ni, “Detection and Positive Reconstruction of Cognitive Distortion Sentences: Mandarin Dataset and Evaluation,” in Findings of the Association for Computational Linguistics ACL 2024, Stroudsburg, PA, USA: Association for Computational Linguistics, 2024, pp. 6686–6701. doi: 10.18653/v1/2024.findings-acl.399.
[14] S. Lim, Y. Kim, C.-H. Choi, J. Sohn, and B.-H. Kim, “ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification,” Mar. 2024.
[15] N. P. Sastra, Linawati, G. Sukadarmika, I. P. G. H. Suputra, N. M. Ariwilani, and N. L. I. D. Swandi, “Dataset on cognitive distortions for text classification in Indonesian language,” Data Brief, vol. 61, p. 111836, Aug. 2025, doi: 10.1016/j.dib.2025.111836.
[16] G. I. Winata et al., “NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages,” in Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Stroudsburg, PA, USA: Association for Computational Linguistics, 2023, pp. 815–834. doi: 10.18653/v1/2023.eacl-main.57.
[17] S. Cahyawijaya et al., “NusaCrowd: Open Source Initiative for Indonesian NLP Resources,” in Findings of the Association for Computational Linguistics: ACL 2023, Stroudsburg, PA, USA: Association for Computational Linguistics, 2023, pp. 13745–13818. doi: 10.18653/v1/2023.findings-acl.868.
[18] F. Koto, J. H. Lau, and T. Baldwin, “IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Stroudsburg, PA, USA: Association for Computational Linguistics, 2021, pp. 10660–10668. doi: 10.18653/v1/2021.emnlp-main.833.
[19] W. Zhang, L. Deng, L. Zhang, and D. Wu, “A Survey on Negative Transfer,” IEEE/CAA Journal of Automatica Sinica, vol. 10, no. 2, pp. 305–329, Feb. 2023, doi: 10.1109/JAS.2022.106004.
[20] N. K. Nissa and E. Yulianti, “Multi-label text classification of Indonesian customer reviews using bidirectional encoder representations from transformers language model,” International Journal of Electrical and Computer Engineering (IJECE), vol. 13, no. 5, p. 5641, Oct. 2023, doi: 10.11591/ijece.v13i5.pp5641-5652.
[21] Q. Chen, J. Du, A. Allot, and Z. Lu, “LitMC-BERT: Transformer-Based Multi-Label Classification of Biomedical Literature With An Application on COVID-19 Literature Curation,” IEEE/ACM Trans. Comput. Biol. Bioinform., vol. 19, no. 5, pp. 2584–2595, Sep. 2022, doi: 10.1109/TCBB.2022.3173562.
[22] Muhammad Mursyid, A. Setiawan, and M. Arifin, “Implementation of IndoBERT in Sentiment Analysis of Free Nutritious Meal Programs on the X Social Media Platform,” Jurnal Teknologi Informasi dan Pendidikan, vol. 19, no. 1, pp. 1228–1242, Mar. 2026, doi: 10.24036/jtip.v19i1.1104.
[23] R. Budianoor, S. W. Saputro, F. Abadi, R. A. Nugroho, and A. Farmadi, “Quantifying the Impact of Text Preprocessing on IndoBERT Fine-Tuning for Indonesian Informal Culinary Sentiment Analysis,” Journal of Computing Theories and Applications, vol. 3, no. 4, pp. 564–581, May 2026, doi: 10.62411/jcta.15980.
[24] K. Martskvishvili, M. Panjikidze, T. Kamushadze, N. Garuchava, and D. J. A. Dozois, “Measuring the Thinking Styles: Psychometric Properties of the Georgian Version of the Cognitive Distortion Scale,” J. Cogn. Psychother., vol. 35, no. 4, pp. 268–289, Nov. 2021, doi: 10.1891/JCPSY-D-19-00025.
[25] F. Moons and E. Vandervieren, “Measuring agreement among several raters classifying subjects into one or more (hierarchical) categories: A generalization of Fleiss’ kappa,” Behav. Res. Methods, vol. 57, no. 10, p. 287, Sep. 2025, doi: 10.3758/s13428-025-02746-8.
[26] K. L. Gwet, Handbook of Inter-Rater Reliability Fith Edition The Definitive Guide to Measuring the Extent of Agreement Among Raters Volume 1 Analysis of Categorical Ratings, Fifth Edition. AgreeStat Analytics, 2021. [Online]. Available: https://sites.fastspring.com/agreestat/instant/cac5ed978_1_7923_5463_2ehttps://agreestat.com/books/cac5/https://agreestat.com/books/
[27] A. N. Uma, T. Fornaciari, D. Hovy, S. Paun, B. Plank, and M. Poesio, “Learning from Disagreement: A Survey,” Journal of Artificial Intelligence Research, vol. 72, pp. 1385–1470, Dec. 2021, doi: 10.1613/jair.1.12752.
[28] A. Fatwanto, F. Zamakhsyari, and R. Ndungi, “A Systematic Literature Review of BERT-based Models for Natural Language Processing Tasks,” JURNAL INFOTEL, vol. 16, no. 4, pp. 713–728, Dec. 2024, doi: 10.20895/infotel.v16i4.1206.
[29] N. Raghunathan and K. Saravanakumar, “Challenges and Issues in Sentiment Analysis: A Comprehensive Survey,” IEEE Access, vol. 11, pp. 69626–69642, 2023, doi: 10.1109/ACCESS.2023.3293041.
[30] F. Indriani, R. A. Nugroho, M. R. Faisal, and D. Kartini, “Comparative Evaluation of IndoBERT, IndoBERTweet, and mBERT for Multilabel Student Feedback Classification,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 8, no. 6, pp. 748–757, Dec. 2024, doi: 10.29207/resti.v8i6.6100.
[31] A. N. Tarekegn, M. Giacobini, and K. Michalak, “A review of methods for imbalanced multi-label classification,” Pattern Recognit., vol. 118, p. 107965, Oct. 2021, doi: 10.1016/j.patcog.2021.107965.
[32] Y. Xing, J. Z. Zhang, V. C. Storey, and A. Koohang, “Diving into the divide: a systematic review of cognitive bias-based polarization on social media,” Journal of Enterprise Information Management, vol. 37, no. 1, pp. 259–287, Feb. 2024, doi: 10.1108/JEIM-09-2023-0459
[33] M. Cinelli, G. De Francisci Morales, A. Galeazzi, W. Quattrociocchi, and M. Starnini, “The echo chamber effect on social media,” Proceedings of the National Academy of Sciences, vol. 118, no. 9, Mar. 2021, doi: 10.1073/pnas.2023301118.
