Food is always close to us, along with the growing population, the food business will continue to grow. During the Covid-19 Pandemic, even though many people stay at home, they occasionally want to buy their favorite food outside the home, whether it's buying directly onsite or online. The aspect categorization is carried out by combining the LDA method and Semantic Similarity to categorize tweets into four culinary aspects (1) Price, (2) Taste, (3) Place, and (4) Service. The best performance of aspect categorization is by combining the LDA and TF-ICF 100% for term extension. Next, the classification stage with Word Embedding to extract features using GloVe and SVM with three-parameter modifications of the SVC method: (1) C-SVC, (2) Linear SVC, and (3) SVCnu with various kernel changes to get the best results. Then an increase in classification accuracy is carried out using SentiCircle. The results of this study show that aspects of service (4) Has a review with a high negative sentiment that reaches 10.869% compared to sentiment reviews on other aspects in percent (price: 4.348, taste: 6.522, place: 4.521) so that business owners culinary needs to make improvements to pay more attention to customer service to reduce the number of negative reviews on this service aspect. The results also show that changes in sentiment (on positive or negative sentiment) are influenced by the aspect of each review.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.