KLASIFIKASI SUPPORT VECTOR MACHINE BERBASIS PARTICLE SWARM OPTIMIZATION UNTUK ANALISA SENTIMEN PENGGUNA APLIKASI PEDULILINDUNGI

Abstract

Covid-19 is an infectious disease that has spread to Indonesia. Monitoring the spread of Covid-19 in Indonesia is handled by the Ministry of Communication and Information (KOMINFO) by creating the PeduliLindung application which can be found on Google Play. Users will choose applications that have good reviews, but monitoring reviews from the public is not easy, so the author wants to know the analysis of user reviews of the PeduliLindung application based on user comments using the Support Vector Machine algorithm based on Particle Swarm Optimization. The test results with an accuracy value = 93.0% and AUC value = 0.977. For this reason, the application of the PSO-based Support Vector Machine in this research has a higher accuracy so that it can be used to provide solutions to sentiment analysis problems in reviewing comments from the Pedulilindungi application users on google play.