<![CDATA[The expansion of the digital gaming sector has been accompanied by a growing volume of user feedback on application marketplaces, including reviews of Roblox on the Google Play Store. This research examines user sentiment toward Roblox by combining a lexicon-based labeling scheme that uses the Indonesian Sentiment Lexicon (InSet) with a Support Vector Machine (SVM) classifier. A total of 1,000,000 reviews were collected through scraping. The raw corpus was then processed through cleaning, case folding, normalization, tokenization, stopword removal, and duplicate elimination, leaving 772,599 usable reviews. Sentiment labels were assigned with the InSet lexicon, while TF-IDF was applied to convert the text into numerical features before SVM classification. The labeling stage produced 57.58% reviews in the “Good” class and 42.42% in the “Not Good” class. Using a linear kernel, the SVM achieved 94% accuracy, with precision, recall, and F1-score all reaching 0.94. These findings show that the InSet-SVM combination is suitable for categorizing Roblox review sentiment and for describing users’ overall perceptions of the application.]]>
Copyrights © 2026
