Sentiment Analysis Towards Kartu Prakerja Using Text Mining with Support Vector Machine and Radial Basis Function Kernel

Background: The introduction of Kartu Prakerja (Pre-employment Card) Programme, henceforth KPP, which was claimed to have launched in order improve the quality workforce, spurred controversy among members public. discussion covered amount budget, training materials and operations brought out various reactions. Opinions could be largely divided into groups: positive negative sentiments.Objective: This research aims propose an automated sentiment analysis that focuses on KPP. findings are expected useful evaluating services facilities provided.Methods: In analysis, Support Vector Machine (SVM) text mining used with Radial Basis Function (RBF) kernel. data consisted 500 tweets from July October 2020, were two sets: 80% for 20% testing five-fold cross validation.Results: results descriptive show total tweets, 60% sentiments 40% sentiments. classification average accuracy, sensitivity, specificity, prediction values 85.20%; 91.68%; 75.75%; 85.03%; 86.04%, respectively.Conclusion: SVM RBF kernel performs well opinion classification. method can understand similar future. KPP case, inform stakeholders programmes Keywords: Prakerja, Sentiment Analysis, Machine, Text Mining,