PERBANDINGAN METODE SUPPORT VECTOR MACHINE DAN DECISION TREE UNTUK ANALISIS SENTIMEN REVIEW KOMENTAR PADA APLIKASI SITUS PENJUALAN ONLINE

Internet shopping can be done easily using e-commerce applications. Shopee is one of the reputable e-commerce applications in Indonesia. In a system or e-commerce application must have flaws that are often felt by its users. By analyzing application users, companies can understand the shortcomings of the application and the expectations of its users. The purpose of this study is to conduct a sentiment analysis using review data found on the Google Play website to find out things that are often reviewed by users. Labeling was then carried out and analyzed using Support Vector Machine and Decision Tree to classify reviews based on positive sentiment class categories and negative sentiment classes. Then visualize the information that is often reviewed using charts. Through classification, the greatest accuracy results are obtained by using Support Vector Machine of 82.19%. As well as positive reviews that are often reviewed, namely "shopping" while negative reviews are often reviewed, namely "network". The word "network" often appears together with the word "problematic", which indicates that this application still has problems with its network.