This research focused on the performance comparison of the classification algorithm, and word frequency visualization from the public in the form of word cloud where the data were taken is about the scope of PSBB implementation and combined with New Normal implementation. The purpose of this research is to determine the economic impact of these two policies on the community. Furthermore, this research can be used as a reference for consideration in making further policy decisions. Then, classified into positive or negative categories using three algorithms, namely Bernoulli Naive Bayes (BNB), Support Vector Machine (SVM), and K-Nearest Neighbor (K-NN) with the Hyperparameter Tuning technique applied to obtain a more effective combination of hyperparameter values. Each algorithm was analyzed to determine the best results in accuracy, precision, recall, and f1-score. Furthermore, the results were used as a visualization modelling word for material evaluation of the policies applied.