Abstract:
During the COVID-19 pandemic, most people relied on the internet to find information,
including health information. The process of digitizing the world of health, especially
during a pandemic, was actually enough to help people get their right to health. The
existence of digital health applications certainly will not replace the function of doctors
and medical personnel in the world of health. Alodokter is a health platform in
Indonesia. Alodokter application users can provide reviews of these application
services through the review feature on the Google Play Store. The existence of this
feature is one of the considerations for prospective users to download applications and
can be used as an evaluation to improve application performance. Therefore, it is
necessary to carry out a sentiment analysis to see an overview of the perceptions of
Alodokter application users on the Google Play Store. In this study, data collection was
carried out using web scraping techniques using Google Colab. The data used is user
review data after it was determined that COVID-19 entered Indonesia, namely from
March 2020 to May 2020 with a total of 13,225 review data. The method used in this
study is Random Forest, this method produces classification accuracy performance with
an accuracy rate of 96.1% as measured using the Confusion Matrix. Based on the
accuracy value, it can be seen that Random Forest has good performance in processing
big data.
