Fake news detection using naïve Bayes and long short term memory algorithms

Sarra Senhadji, Rania Azad San Ahmed


Information and communication technologies have revolutionized the numerical world by offering the freedom to publish and share all types of information. Unfortunately, not all information circulated on the internet is accurate, which can have serious consequences, including misleading readers. Detecting false news is a complicated task to overcome. Massive studies focus on using machine and deep learning techniques in an attempt to classify the news as authentic or not. The goal of this research is an attempt to glance and evaluate how naïve bayes (NB) and long short-term memory (LSTM) classifiers can be used to positively identify fake news. The outcomes of this experiment reveal that LSTM achieves an accuracy of 92 percent over naive bayes. Moreover, the findings of the proposed approach’s results outperform the related work results.


Deep learning; Fake news detection; LSTM; Machine learning; Naïve bayes;

Full Text:


DOI: http://doi.org/10.11591/ijai.v11.i2.pp746-752


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

IAES International Journal of Artificial Intelligence (IJ-AI)
ISSN/e-ISSN 2089-4872/2252-8938 
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

View IJAI Stats