FUEL INCREASE SENTIMENT ANALYSIS USING SUPPORT VECTOR MACHINE WITH PARTICLE SWARM OPTIMIZATION AND GENETIC ALGORITHM AS FEATURE SELECTION

BBM, or fuel oil, is one of the essential needs Indonesian people. The government's policy regarding increase in prices raises many opinions from public. Twitter social media that people often use to express on a topic. In this study, sentiment analysis was carried out public opinion price media. This research expected help determine with positive, neutral and negative sentiments. method used Support Vector Machine (SVM) classification algorithm. results accuracy SVM were compared by adding feature selection process. Particle Swarm Optimization (PSO) Genetic Algorithm (GA) algorithms are for method. After several experiments using three methods, Radial Basis Function (RBF) kernel produced best 71.2%. combination RBF PSO kernels obtained an 68.84%, GA methods 69.52%.