Aspect-Based Sentiment Analysis on Application Review using Convolutional Neural Network

As an obligatory application during the COVID-19 pandemic by Indonesians, PeduliLindungi must have provided outstanding quality services to its users. However, as of December 2021, users’ sentiment toward and service was still low, with rating 3.6 out 5 on Google Play Store. This study uses text mining techniques for Aspect-Based Sentiment Analysis (ABSA) task in review, a analysis based aspect category application. aims classify aspects provide insight knowledge improve The ABSA method used this is classification sentiments using Convolutional Neural Network (CNN) algorithm. results showed that CNN model could produce such good performance f1 score 92.23% 95.13% classification. user modelling dominance negative eight application, namely Visual Experience, Scan – Check-in/Out, Vaccine Certificate, eHac, COVID Test, Register/Login, Performance Stability, Privacy, Data, Security.
 Index Terms—Aspect-Based Analysis, Convolution Network, PeduliLindungi, Text Classification, Mining.