Analisis Sentimen Pengguna Terhadap Tiga Fitur Utama WPS Office Menggunakan Algoritma Support Vector Machine

This study aims to analyze the sentiment of WPS Office user reviews using the Support Vector Machine (SVM) method. A total of 6,110 reviews were collected, with 1,222 reviews used as testing data. The experimental results show that the SVM model achieved an accuracy of 94.35%, a precision of 93.71%, a recall of 95.09%, and an F1-score of 94.39%, indicating that the model is highly effective in classifying user review sentiments. The visualization results reveal that most reviews were obtained from Google Play Store, Indonesia was dominated by positive sentiment, while the United States had more negative than positive reviews. In addition, the Writer (Word/Docs), Spreadsheet (Excel), and Presentation (PPT) features received more negative than positive sentiments. Therefore, the proposed SVM model is considered effective and suitable for automatically analyzing and classifying the sentiment of WPS Office user reviews.