This study aims to determine the implementation of Fuzzy Sugeno in classifying textual data obtained from Twitter so as to determine the polarity of public opinion regarding PPKM policies and Covid-19 vaccinations. This study uses primary data via Twitter related to COVID-19 vaccination and PPKM policies in Indonesia starting from February 9, 2021 to January 17, 2022. There are several stages carried out, namely data collection, data pre-processing, data labeling, data weighting. , identification of membership functions, determination of fuzzy sets, formation of classification systems, and evaluation of classification results. The results of this study explain that Fuzzy Sugeno's performance in classifying tweets is quite good with an average accuracy of 89.13%. Meanwhile, public opinion regarding PPKM policies and Covid-19 vaccinations tends to be balanced with 36.92% of tweets classified as positive sentiments, 22.85% negative sentiments, and another 40.23% classified as neutral sentiments. In addition, the fuzzy set that is formed based on the data observation method is very well done because it is able to adjust the frequency of the data in each category. This really helps improve the performance of the built classification system.