Optimization Sentimen Analysis using CRISP-DM and Naive Bayes Methods Implemented on Social Media

Freedom of expression on social media Twitter not always give positive value, because sometimes can contains negative things such as fake news, spreads hate speech, and racism, where these kinds tweet be categorized an act Cyberbullying. Where this cyberbullying tends to increase every time. The aim study is use the Naïve Bayes method in classifying types sentiment Twitter. keyword used Saipul Jamil, was taken September 2021. A total 18,067 tweets were collected then they will labelled with a or value. This also uses CRIPS-DM which consist Business Understanding, Data Preparation, Modeling, Evaluation, Deployment stages. results obtained value Accuracy (85.6%), Negative Recall (82.1%), Positive (90.23%), Precision (91.76%) (79.18%).