<![CDATA[The great flood disaster that hit the South Kalimantan region caused conversation and debate among the community and government, especially on Twitter which was trending, and thousands of tweets appeared on Twitter with the hashtags #PrayForKalsel, and #KalselJugaIndonesia. The tweets of the public and the government clashed for their own defense of the truth and gave rise to many positive and negative opinions. Twitter is now a place to chat and complain about various groups. For this research, it is hoped that it can help and make it easier to conduct research using public opinion on Twitter that contains positive or negative opinions. The method used in this study is using Naive Bayes, the process of this system starts from the data preprocessing process which includes case folding, tokenization, filtering, normalization, and finally stemming then word weighting using Raw TF and the classification process used is Naive Bayes. The data used comes from twitter which is taken by crawling and scrapping using the hashtags #PrayForKalsel, and #KalselJugaIndonesia with a total of 520 data. The data was taken using the Twitter API. using the confusion matrix test from the 5 experiments, the average value reaches an accuracy of 0.81, a precision of 0.81, a recall of 0.81, and an f-measure of 0.81, and the highest test value is an accuracy of 0.88, a precision of 0.89, recall 0.87, and f-measure 0.87.]]>
Copyrights © 2021
