Fake News Detection in the Framework of Decision-Making System through Graph Neural Network

The rapid growth of the number of fake news has become a serious threat to the credibility of the governments of many countries. The extensive use of social platforms contributes to the creation and dissemination of fake news. This is actualize the task of fake news detection. Much research has already focused on this. Modern methods of detecting fake news rely heavily on textual information, examining the extracted news content or writing style based on internal knowledge. However, intentional rumors can mask the style of writing, bypassing languages and text patterns. In order to combat the spread of fake news, methods of automatic detection based on artificial intelligence and machine learning were studied. In a world where millions of articles are deleted and published every minute, this cannot be done effectively manually. The solution may be to develop a system to provide reliable automated assessment systems or to assess the reliability of different publishers and news contexts using deep learning techniques, namely graph neural networks with an inductive structure.