News has been disseminated swiftly via the internet due to the rapid growth of information technology. The rapid spreading of news often confuses because the truth cannot be ascertained. Additionally, online social media is becoming increasingly popular, making it an excellent environment for propagating false information, including misinformation, phony reviews, advertising, rumors, political remarks, innuendo, etc. This study's specific goal is to classify data using a data mining approach model called text mining so that a system can automatically do the classification. As a result, the study will produce a dataset, which can then be used to create an application using data mining's ability to predict breaking news. An application was produced by employing data mining to forecast recent news. This study was able to classify data using a naive Bayes data mining approach model so that a system can automatically do the classification. The study produced an accuracy of 77% obtained with training data of 82%. From 994 contents, the classification of misleading content reached 33.9%, false content as many as 24.85%, imitation content was 13.48%, fake content reached 11.07%, manipulated content was 9.86%, parody content was 3.22%, satire content was 2.31%, and connection content as many as 1.31%. This study then visualizes the results using bar charts and word clouds. This work also produced datasets with the naïve Bayes method of news data and news that has been valid. Afterward, the dataset will be used in making applications to produce prototypes of computer program applications.