The Fight Against Fiction: Leveraging AI for Fake News Detection

This study aims to evaluate the performance of three machine learning algorithms namely Logistic Regression, Naïve Bayes, and Random Forest in classifying fake news. The research methods include data collection from various news sources, text preprocessing to improve data quality, and context-based feature engineering that considers temporal, linguistic, and named entity aspects. Furthermore, the model is developed using a machine learning approach that integrates ensemble techniques to improve prediction accuracy. Evaluation was conducted using accuracy, precision, accuracy, and F1 score metrics. The experimental results showed that Random Forest performed best with an accuracy of 93.00%, superior to Naïve Bayes (89.96%) and Logistic Regression (91.00%). This analysis confirms that algorithm selection should be tailored to the specific needs of the project, with Random Forest being a more reliable choice for scenarios that require high accuracy and robustness to data complexity. The findings are expected to contribute to the development of fake news detection systems that are more effective and adaptive to the dynamics of information in the digital world.