<![CDATA[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]]>
Copyrights © 2026
