Analisis Sentimen Ulasan Aplikasi Wetv Untuk Peningkatan Layanan Menggunakan Metode Support Vector Machine

Abstract

Wetv is an online streaming media that has been running since 2019. Wetv has many user reviews from various applications. The rating consists of positive, neutral and negative. The response is used to determine sentiment by using the support vector machine classification method. This study took 12,000 comments from the Google Play Store, this study used preprocessing namely, cleaning, case folding, tokenizing, normalization, stopword removal, and steaming, then to the TF-IDF stage and the final results were tested with a fusion matrix with the Python program, the score results highest from the acquisition test process with accuracy of 0.76%, precision of 0.77%, recall of 0.79%, and f1 score of 0.78, in a dataset of 90% training data and 10% test data. Based on the research results of the Support Vector Machine method which is known to be good in the process of requesting negative responses on WeTV.