<![CDATA[The COVID-19 pandemic caused a crisis in global economic growth. The impact of injuries due to the COVID-19 pandemic has also caused price increases and an increase in the inflation rate. Inflation is a price increase caused by a certain factor so that it has an impact on the prices of nearby goods which increase the circulation of money in society to increase. Many people expressed their various opinions or criticisms of the post-COVID-19 price increase policy on social media, one of which was via Twitter. Sentiment analysis was carried out to see how public sentiment is towards the price increase policy after the COVID-19 pandemic, and these sentiments are combined into multiclasses, namely positive, negative and neutral sentiments. So that this sentiment can later be used as material for evaluation regarding the post-COVID-19 price increase policy. This study aims to see and compare the accuracy of the two classification methods, namely K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) in the sentiment classification process. The data used was 5989 tweets with the keywords ""Stuffets Go Up Post-Pandemic", "Fuel Goes Up", "Inflation 2022", "Covid19 Inflation", "Inflation Post-Pandemic" with a data collection period from August to October 2022. The data obtained then enter the text preprocessing stage before later entering the classification stage. The results obtained after carrying out the classification using the K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) methods show that the Support Vector Machine (SVM) method has a higher accuracy of 79%, while the K-Nearest Neighbor (K -NN) has an accuracy of 54%.]]>
