This study aims to analyze public sentiment on the social media platform X regarding the Indonesian Ulema Council (MUI)'s fatwa calling for a boycott of pro-Israel products. The method used is the Gated Recurrent Unit (GRU), a deep learning architecture known for its effectiveness in processing sequential data. Primary data were collected from user tweets containing the hashtags #fatwamui and #boikotproduk, while secondary data were obtained from relevant literature. The research stages include data preprocessing (case folding, tokenization, stopword removal, and stemming), feature extraction (BoW and TF-IDF), and sentiment classification using the GRU model. Evaluation results show that the model achieved an accuracy of up to 89%, with a precision of 90.9%, recall of 87%, and F1-score of 87%, indicating a strong and balanced performance in classifying both positive and negative sentiments. These findings affirm that the GRU approach is effective for Indonesian-language sentiment analysis, particularly in the context of sensitive socio-religious issues, and has the potential to serve as a reference for policy-making based on public opinion.
You may also start an advanced similarity search for this article.