<![CDATA[The spread of the coronavirus pandemic in early 2020 created global tension, prompting preventive and control efforts worldwide, including in Indonesia. The government's response to this situation involved various proactive measures, one of which was the development of the PeduliLindungi application. This application serves as a platform that enables the community to contribute by sharing location data during activities. Its goal is to facilitate the tracking of contact history with individuals infected with Covid-19 in Indonesia. Despite having a positive impact on controlling the spread of the virus, the widespread use of the PeduliLindungi application has generated diverse opinions among users, reflected in feedback on the Google Playstore. To manage the diverse textual feedback data, a sentiment analysis approach emerges as a solution. In this context, this research proposes the implementation of the Long Short-Term Memory (LSTM) method to analyze sentiment feedback on the PeduliLindungi application. Achieving an accuracy of 92.51%, with 69.3% negative aspects, 18.3% positive, and 12.4% neutral, this analysis provides valuable insights for application developers and other stakeholders. It is hoped that the results of this research can be used as a guide to enhance the quality and effectiveness of the PeduliLindungi application, aiming for a greater positive impact in addressing public health challenges.]]>
Copyrights © 2024
