Analisis Sentimen Program Makan Siang Gratis di Twitter/X menggunakan Metode BI-LSTM

Abstract

The free lunch program became a widely discussed topic on social media, reflecting public opinion towards the policy. This research aims to analyze public sentiment towards free lunch program to evaluate the policy's effectiveness and understand public perception. Data was collected through web crawling techniques on the Twitter/X platform, resulting in 7,441 data. Processing stages include preprocessing, sentiment labeling using VADER, keyword visualization with wordcloud, and application of word embedding using Word2Vec. The oversampling technique is used to overcome data imbalance. Sentiment classification was developed using Bi-LSTM and evaluated with accuracy, precision, recall, and F1-score. The developed Bi-LSTM model achieved 88.75% accuracy, with 88.9% precision, 88.8% recall, and 88.8% F1-score. Analysis results show that the majority of public responses are positive or neutral, although there were negative sentiments that highlighted potential problems such as corruption and increasing national debt. These results provide insight into public opinion on the free lunch policy and demonstrate the effectiveness of the Bi-LSTM model in social media sentiment classification.