Classification of Public Opinion on the Free Nutritional Meal Program on YouTube Media Using the LSTM Method
For Indonesian policymakers evaluating public opinion on a nutrition program, this is an incremental application of existing LSTM methods to a new domain.
The study applies LSTM to classify public sentiment on Indonesia's Free Nutritious Meal Program from 7,733 YouTube comments, achieving 89% accuracy but with poor positive sentiment detection (F1-score 0.55) due to severe class imbalance (87.7% negative).
Public opinion towards the Free Nutritious Meal Program (MBG) on YouTube social media reflects diverse community responses. This study applies the Long Short-Term Memory (LSTM) method to classify sentiments from 7,733 YouTube comments. The results show that the LSTM model achieves 89% accuracy, with strong performance on negative sentiment (F1-score 0.94) but weaker performance on positive sentiment (F1-score 0.55) due to class imbalance, as negative data account for 87.7% of the dataset. These findings confirm the effectiveness of LSTM for sentiment analysis of Indonesian text while highlighting the challenge of imbalanced data. This research contributes to social media-based public policy evaluation