<![CDATA[Halodoc is a digital healthcare platform that provides users with convenient access to medical services online. This study aims to analyze public sentiment toward the Halodoc application based on 1,416 user reviews collected during the period from July to September 2024. The reviews are categorized into three sentiment classes: positive, negative, and neutral, using the Long Short-Term Memory (LSTM) algorithm. Prior to classification, the Word2Vec technique is applied to transform the words in the reviews into numerical vector representations for processing by the model. The analysis revealed that a portion of the reviews expressed negative sentiments, mainly concerning delays in medication delivery and slow responses from customer service. Model performance evaluation shows that the implementation of the LSTM algorithm optimized with the Adam (Adaptive Moment Estimation) optimizer and a dropout rate of 0.2 achieved the highest accuracy of 89.40% and an F1-score of 88.63%. These results indicate that the model performs very well in classifying sentiments and can be used as a useful tool for understanding user satisfaction with the Halodoc application.]]>
Copyrights © 2025
