Sentiment Analysis of Honkai: Star Rail Indonesian Language Reviews on Google Play Store Using Bidirectional Encoder Representations from Transformers Method

Abstract

Online games are a type of entertainment that is done by humans to have fun and forget all the problems in everyday life. Honkai: Star Rail is a new online game application owned by miHoYo which is currently popular and widely downloaded on the Google Play Store. Reviews on the Honkai: Star Rail app are increasing over time so this makes it difficult for app developers to know past user reviews on their apps. Therefore, the author conducted a study to analyze sentiment towards Honkai: Star Rail application reviews in Indonesian on the Google Play Store using the Bidirectional Encoder Representations from Transformers (BERT) method to determine user sentiment towards the Honkai: Star Rail application and then processed further so that it becomes a record for developers, users, and prospective users of the Honkai: Star Rail application. This study uses Indonesian language review data from users of the Honkai: Star Rail application found on the Google Play Store website as many as 6000 reviews. The BERT method applied in this study consisted of data collection, dataset labeling, data preprocessing, dataset splitting, modeling, model training, and evaluation. Based on the evaluation results that have been carried out on the test data, 97 data are true positive with 27 data are false positive, 4 data are true neutral with 47 data are false neutral, and 381 data are true negative with 37 data are false negative. So, it can be concluded that the model still has difficulty predicting reviews with neutral sentiment but is good enough at predicting reviews with positive and negative sentiment. In addition, the accuracy of the model is 81% with a precision of 63% for positive sentiment reviews, 36% for neutral sentiment reviews, and 89% for negative sentiment reviews.