1-	Title: Fake News Detection in Arabic Media: Comparative Analysis of Machine Learning Algorithms on AFND Dataset
2-	Description: Keeping up with news on social media offers both advantages and challenges. Social platforms enable rapid information dissemination, yet they can also serve as channels for spreading misleading or low-quality content, often labeled as "fake news." The extensive distribution of fake news has serious consequences for both individuals and society at large. As a result, detecting fake news on social media has emerged as a critical research area, drawing growing interest. Identifying fake news across various platforms presents new challenges, as many existing detection methods become less effective or outdated. Fake news is usually crafted to deceive readers, which makes it challenging to spot just by examining the content alone. To improve detection accuracy, it’s important to also consider contextual information, like how users interact with the content on social media. However, studying these interactions isn’t straightforward because they create vast amounts of messy, unorganized, and incomplete data. Recognizing this challenge, our research focuses on evaluating how well three widely-used machine learning algorithms random forest, Naive Bayes, and neural networks can detect fake news. We conducted our experiments on the Arabic Fake News Dataset, a comprehensive dataset that includes over 606,912 articles from various sources categorized by credibility. Results demonstrate that the Naive Bayes algorithm performed particularly well, with high accuracy in distinguishing credible from non-credible articles.
3-	Dataset Information: : AFND Dataset
4-	Code Information: Python 3.11, Anaconda Environment 
5-	Usage Instructions – How to use or load the dataset and code
1-	Install the Anaconda from the official site: https://www.anaconda.com/download.
2-	Open the jupyter notebook in the code file location that included the dataset the requirement file.
3-	Run each cell. 
6-	Requirements:  Machine Learning Libraries: pandas, numpy, scikit-learn, matplotlib, seaborn, imblearn, Visualization: Matplotlib, Seaborn, Algorithms:  RF, NB, Neural Network