Public Sentiment on Indonesia’s Free Nutritious Meal Program: A Mixed-Methods NLP Evaluation

Read full text Summarise with VIRAT
Authors: Firmansyah Ibrahim, Didik Dwi Prasetya, Andi Baso Kaswar, Hardyanti Pratiwi
Cited by: 0
References: 19

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Large-scale nutrition intervention programs such as the Free Nutritious Meal Program (MBG) are likely to attract considerable attention on social media. While conventional evaluation techniques are often too slow to capture rapidly shifting sentiment, this study seeks to determine how sentiment can be evaluated. More specifically, we aimed to identify the key emerging issues. Methodology: In this study, one approach to examining emerging issues is to use a two-stage workflow in Natural Language Processing (NLP). The first step in sentiment analysis is using a transformer model (Indo-RoBERTa) to assign 'Positive', 'Negative', or 'Neutral' to 3,459 public texts from X (Twitter) social media. Secondly, we focused on 1,130 'Negative' texts. We used topic modeling (BERTopic) on this and identified the most critical clusters of issues to map and their relative importance. Results & Conclusions: Negative sentiment involves multiple factors, to which our model successfully highlighted four of the most impactful areas: (1) Financial concerns and budgetary priorities; (2) Responses to particular media coverage (e.g., Kompas); (3) Political general discourse; and (4) Expectations of particular local issues (education issues in Papua). Conclusion: Compared with the gaps in the program's nutrition components, the economic consequences, budget gaps, inequities, and regional policy deficiencies drew more public interest. Implications: The findings point to a clear need for a differentiated and open approach to communicating public policy. This approach should communicate the nutritional value and the need to align messaging with the public for the geographic and budgetary realities.

Fields of Study & Subjects

Sentiment Analysis and Opinion Mining Computational and Text Analysis Methods Public Health and Nutrition

Publication details

Journal / source
Journal of Health and Nutrition Research
Volume
5
Issue
1
Pages
227–235
Publication date
1 April 2026
Language
EN