<![CDATA[Nutritional problems and food insecurity remain critical challenges in Indonesia, especially in underprivileged areas. To address this, the Lamongan City Government launched the Free Nutritious Meal (MBG) program as a public welfare initiative. This study aims to evaluate public opinion on the MBG program using sentiment analysis based on a hybrid machine learning model combining K-Nearest Neighbor (KNN) and Naive Bayes algorithms. A total of 2,261 public comments were collected from social media, online surveys, and interviews. The data underwent preprocessing, feature extraction using TF-IDF, and dual-stage classification—first by topic (Menu, Impact, Schedule, Others) using Naive Bayes, then sentiment classification (positive, negative, neutral) using KNN. Evaluation metrics including accuracy, precision, recall, and F1-Score were applied. Results show that neutral sentiment was the most dominant (41.28%), followed by positive (32.01%) and negative (26.49%). The model achieved an overall accuracy of 87%, with the highest F1-Score of 0.91 in the positive sentiment category. These results demonstrate that the hybrid model effectively captures community perceptions and can support data-driven evaluation of local social programs.]]>
Copyrights © 2025
