The rapid growth of social media use through modern communication methods has led to the spread of fake news globally. For the sake of mitigating this problem, several researchers in Artificial Intelligence have explored the use of machine learning and natural language processing (NLP) techniques to distinguish fake news from believable information. Despite significant progress in detecting fake news in the English language, still the research on detecting fake news for the Arabic Language remaining limited, highlighting evident gaps that need robust solutions. This study comprehensively explores the current detection methods for Arabic-language-based in automating fake news, summarizing the main approaches, findings, and most used datasets. Many research papers were analyzed to represent current trends and identify existing methodological limitations. Based on these insights, this study suggests applying two BERT based models (ARBERT and AraBERT) using two categorized Arabic datasets to evaluate news credibility. This study showed that the proposed detection models achieved a superior accuracy of approximately 85%. It highlights an elevated potential for detecting fake news in the Arabic language and confirms the importance of continuing research to enhance multilingual credibility assessment geared towards specialized fields.
Jabar H. Yousif (Thu,) studied this question.