Implementation of IndoBERT in Sentiment Analysis of Free Nutritious Meal Programs on the X Social Media Platform

Muhammad Mursyid; Arif Setiawan; Muhammad Arifin

doi:10.24036/jtip.v19i1.1104

Authors

Muhammad Mursyid Universitas Muria Kudus
Arif Setiawan Universitas Muria Kudus
Muhammad Arifin Universitas Muria Kudus

DOI:

https://doi.org/10.24036/jtip.v19i1.1104

Keywords:

Sentiment Analysis, Free Nutritious Meals, indoBERT, Social Media X, Natural Language Processing

Abstract

The Free Nutritious Meal Program (MBG) is a strategic initiative by the Indonesian government to improve child nutrition and prevent stunting. However, its implementation has sparked diverse public opinions on social media, which are difficult to analyze manually due to the large volume of data. This study aims to identify public sentiment toward the MBG program through social media X by implementing the IndoBERT model. A total of 4,380 tweets were collected using web scraping techniques with relevant keywords between March and May 2025. The research process included preprocessing (data cleaning, stopword removal, stemming, and tokenization), semi-automatic data labeling, and data division into a 71.97% training set, 8.02% validation set, and 20.01% test set. The model used was the Indonesian RoBERTa Base Sentiment Classifier architecture, which underwent a fine-tuning process for 20 epochs. The results showed that the IndoBERT model achieved an accuracy rate of 80.11% and a weighted average F1-score of 0.8000. Negative sentiment was detected most accurately with an F1-score of 0.8301. Although effective, the model still faces challenges in handling linguistic ambiguity in neutral sentiment and the risk of overfitting. Further research is recommended to expand slang language normalization and apply stricter model regulation techniques.

References

A. S. Purmadani dkk., “Jurnal Bisnis Net Volume : 8 No . 1 Juni , 2025 | ISSN : 2621 -3982 Jurnal Bisnis Net Volume : 8 No . 1 Juni , 2025 | ISSN : 2621 -3982,” no. 1, hal. 323–327, 2025.

M. Basit dan H. Ramadani, “Analisis Implementasi Program Makan Bergizi Gratis Terhadap Perkembangan Ekonomi,” vol. 1, no. 2, hal. 49–54, 2025.

A. Sitanggang, Y. Umaidah, R. I. Adam, U. S. Karawang, dan T. Timur, “ANALISIS SENTIMEN MASYARAKAT TERHADAP PROGRAM MAKAN SIANG GRATIS PADA MEDIA,” vol. 12, no. 3, 2024.

U. M. Kudus dan S. Informasi, “APLIKASI LAZADA MENGGUNAKAN METODE NAIVE BAYES,” vol. 14, no. 1, hal. 23–30, 2024.

W. Romadhona dan R. A. Isnain, “Analisis Sentimen Pengguna Media Sosial Terhadap Kebijakan Kenaikan Pajak Hiburan Menggunakan Metode SVM (Support Vector Machine),” J. Ilm. Penelit. dan Pembelajaran Inform., vol. 9, no. 4, hal. 2185–2195, 2024, doi: https://doi.org/10.29100/jipi.v9i4.5603.

A. Syahrir, Harlinda, dan F. Umar, “Analisis Sentimen Masyarakat Terhadap Kebijakan Pemerintah Vaksinasi Booster 2 Menggunakan Metode Naïve Bayes Classifier,” Zo. J. Sist. Inf., vol. 4, no. 1, hal. 347–359, 2023, doi: https://doi.org/10.33096/busiti.v4i4.1835.

R. D. Himawan dan E. Eliyani, “Perbandingan Akurasi Analisis Sentimen Tweet terhadap Pemerintah Provinsi DKI Jakarta di Masa Pandemi,” J. Edukasi dan Penelit. Inform., vol. 7, no. 1, hal. 58, 2021, doi: 10.26418/jp.v7i1.41728.

A. B. Sasmita, B. Rahayudi, dan L. Muflikhah, “Analisis Sentimen Komentar pada Media Sosial Twitter tentang PPKM Covid-19 di Indonesia dengan Metode Naïve Bayes,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 6, no. 3, hal. 1208–1214, 2022, [Daring]. Tersedia pada: http://j-ptiik.ub.ac.id

B. P. Aji, C. Sri, dan K. Aditya, “Klasifikasi Sentimen Ulasan Produk pada Platform E-Commerce di Indonesia dengan Menggunakan Model Pre-Trained IndoBERT,” vol. 6, no. 4, 2025, doi: 10.47065/bits.v6i4.6968.

F. Koto dan T. Baldwin, “IndoLEM and IndoBERT : A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” hal. 757–770, 2020.

J. Teknologi dan A. Alfarel, “Sentiment Analysis of Telkom University using the Long Short- Term Memory and Word2Vec Feature Expansion,” vol. 17, no. 2, hal. 468–481, 2024.

S. R. Putri, M. Arifin, P. Studi, S. Informasi, F. Teknik, dan U. M. Kudus, “Analisis Sentimen Publik terhadap Nadiem Makarim sebagai Mendikbudrisktek menggunakan Support Vector Machine ( SVM ) Public Sentiment Analysis of Nadiem Makarim as Minister of using Support Vector Machine ( SVM ),” vol. 14, hal. 826–834, 2025.

A. Syaifudin dkk., “Analisis Sentimen Ulasan Pengguna Aplikasi KitaLulus pada Google Play Store dengan menggunakan algoritma Support Vector Machine ( SVM ) Sentiment Analysis of User Reviews of the KitaLulus Application on Google Play Store using the Support Vector Machine ( SVM ) Algorithm,” vol. 14, no. Cv, hal. 2519–2530, 2025.

D. A. Dzulhijjah, H. Sanjaya, A. Said, W. Hidayat, dan A. Yulistia, “Perbandingan Metode Random Forest dan KNN pada Analisis Sentimen Twitter,” hal. 767–772.

J. Sanjaya, B. Priyatna, dan S. S. Hilabi, “Analisis Sentimen Terhadap Opini Proyek Kereta Cepat Menggunakan Metode Naïve Bayes Classifier,” vol. 14, no. 1, hal. 263–270, 2024.

W. Ramadlan, M. Arifin, D. L. Fithri, dan P. Setiaji, “ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI SPOTIFY DI GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA NAIVE BAYES,” vol. 9, no. 2, hal. 3600–3607, 2025.

B. Wilie dkk., “IndoNLU : Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” hal. 843–857, 2020.

V. Anggraeni, Y. Sibaroni, dan S. S. Prasetyowati, “Sentiment Analysis of 2024 Election Reviews in Twitter using BERT with Emoticon Feature Extraction,” vol. 18, no. 2, hal. 955–967, 2025.

U. Fathon, M. Arifin, dan A. Setiawan, “Analisis Sentimen Ulasan Pengguna Aplikasi Crunchyroll , iQIYI , Wibuku di Google Play Store Menggunakan Metode Random Forest,” vol. 7, hal. 63–72, 2025.

R. Apriliyanti, D. Kurniadi, D. Novaliendry, dan S. Rahmadika, “Real-Time Color Classification of Objects with an Improved MobileNetV2 CNN Model,” vol. 18, no. 2, 2025.