Steam is a widely used digital game distribution platform with millions of users worldwide. The abundance of user reviews on the Google Play Store serves as a valuable source for analyzing user perceptions and satisfaction regarding the application. Therefore, this study performs sentiment analysis to understand user opinions about the Steam app. This research employs the Naive Bayes algorithm to classify user reviews into two sentiment categories: positive and negative. The process begins with collecting user reviews from the Google Play Store using web scraping techniques. The data then undergo preprocessing steps such as case folding, cleaning, tokenization, stopwords removal, and stemming to improve its quality. TF-IDF is used for feature extraction from the review texts, which are then used as input for the Naive Bayes Classifier model. The model is trained with training data and evaluated with testing data that has been previously split. Model performance is evaluated using a Confusion Matrix and metrics such as accuracy, precision, recall, and F1-score. The results show that the Naive Bayes model achieves an average accuracy of 84% in classifying sentiment. These findings indicate that the method is effective in understanding user opinions about the Steam application. This research is expected to provide insights for developers to improve application quality based on user feedback
Kho et al. (Sat,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: