Hoax news identification using machine learning model from online media in Bahasa Indonesia



  • Inggrid Yanuar Risca Pratiwi Politeknik Masamy International
  • Anggit Ferdita Nugraha Universitas Amikom Yogyakarta


classification, fake news, hoax detection, online media, naïve bayes


Information and communication technology that’s developing is one of the main triggers of the information explosion today. Nowadays, various news content is not only easy to obtain but also easy to produce through various platforms on the internet, including popular online media, such as blogs and websites. So a lot of news content on blogs and websites that are currently being circulated leads to fake news content (hoaxes) that can mislead the perception and thoughts of the readers. Therefore, it is important to develop a system that can detect the presence of fake news content to minimize the losses caused by the presence of fake news content. In this study, the Naive Bayes algorithm is proposed as a machine learning model that will be used to detect fake news content in Indonesian language online media. As a result, the global accuracy value reached 71% with recall, precision, and F1-Score values as a whole above 70% which indicates that the proposed model can detect fake news content quite well.


Download data is not yet available.



How to Cite

Inggrid Yanuar Risca Pratiwi, & Anggit Ferdita Nugraha. (2022). Hoax news identification using machine learning model from online media in Bahasa Indonesia. Matrix : Jurnal Manajemen Teknologi Dan Informatika, 12(2), 58–67. https://doi.org/10.31940/matrix.v12i2.58-67