Sentiment analysis is one of the topics that recently getting more popular on political field or government-related things. Analyzing citizens' view of the government, including Governor and Vice Governor of DKI Jakarta for 2017-2022 period, is one of tasks that can be done using sentiment analysis. Data related to that topic ar e gathered from Twitter and Instagram for further analysis. N-gram, emoji, and all-caps is used as features to classify sentiment of each item. Based on the experiment, those features can help to increase classification performance. Naïve Bayes, Random Forest, and SVM algorithm are compared to select the best algorithm out of those three algorithms. Based on the experiment, SVM get the best result with highest accuracy and F1-score on both domains. The result of the classification shows that citizens tend to have neutral view on Governor and Vice Governor of DKI Jakarta for 2017-2022 period on their first year of governance. In addition, there are more positives than negatives on citizens' view.