FAKE NEWS DETECTION USINGMACHINE LEARNING

The rapid spread of fake news poses a critical challenge in today’s digital era, demanding efficient and adaptive detection techniques. This study investigates the application of the Passive-Aggressive Classifier, a machine learning algorithm well-suited for online learning environments, to identify and combat misinformation.By employing a dataset of news articles that had been labeled, the model was instructed to distinguish between genuine and false information.The initial processing steps involved breaking down the text into tokens, normalizing the text, andutilizing TF-IDF (Term Frequency-Inverse Document Frequency) to convert textual information into numerical formats by extracting features.The classifier's effectiveness was assessed through key performance metrics, including accuracy, precision, recall, and F1-score. Experimental results indicate that the Passive-Aggressive Classifier delivers high accuracy and adaptability, making it a promising solution for real-time fake news detection. This research underscores the potential of adaptive learning models in strengthening automated misinformation detection systems, contributing to the broader goal of preserving the reliability of online information