<![CDATA[The current digital era allows people to consult about health digitally, with applications such as Halodoc which are widely used for health consultations and purchasing medicines. This research aims to measure the accuracy of reviews and evaluate the performance of the Naïve Bayes algorithm in the sentiment analysis classification of users of the Halodoc application. The Naïve Bayes algorithm is applied to identify user sentiment which is divided into three categories: positive, negative and neutral. The analysis results show that with a train-test split of 10%, the application has a positive sentiment level of 94%, negative 63%, neutral 0%, and accuracy 85%. With a train-test split of 20%, the results were 93% positive, 69% negative, 13% neutral, and 86% accuracy. Meanwhile, with a train-test split of 30%, the results were positive 92%, negative 66%, neutral 0.9%, and accuracy 84%. This research provides new knowledge about the effectiveness of the Naïve Bayes algorithm in sentiment analysis in health applications, as well as revealing the level of user satisfaction with the Halodoc application.]]>
Copyrights © 2024
