<![CDATA[Quick commerce services provide shopping convenience with flexible ordering processes unrestricted by time and location, along with rapid delivery, typically within 10–30 minutes. This study analyzes user sentiment towards the quick commerce application Segari, based on reviews available on the Google Play Store. The objective is to develop a system capable of analyzing and categorizing reviews based on user opinions, sentiments, and emotions using the Bidirectional Encoder Representations from Transformers (BERT) method. The dataset of reviews was collected using web scraping techniques and underwent pre-processing steps, including case folding, data cleaning, tokenization, and normalization. The model was trained with a learning rate of 3e-5, 5 epochs, and a batch size of 32. The study achieved an accurate score of 89%, with precision scores of 91% for positive sentiment, 83% for negative sentiment, and 69% for neutral sentiment. This research provides significant insights into user sentiment towards the Segari application and serves as a reference for further development in quick commerce services.]]>
Copyrights © 2025
