Published Paper Details:

The exponential rise of social media and digital news platforms has accelerated the dissemination of information, which often includes a substantial portion of misleading or fabricated content, widely known as fake news. This study proposes an integrated framework for misinformation utilizing machine learning methodologies. Through the application of (NLP) techniques and supervised learning models, the system efficiently classifies news articles as authentic or deceptive with notable accuracy. To extract semantic and syntactic characteristics from textual data, approaches such as (TF-IDF) and word embeddings are incorporated. The research further analyzes the performance of diverse machine algorithms, including logistic regression, random forest, and (LSTM) networks, on benchmark datasets. Findings indicate that learning approaches, particularly LSTM, surpass conventional models in capturing subtle patterns linked with fake news. Overall, this work emphasizes the importance of AI-based strategies in addressing misinformation and fostering trustworthy information sharing in the digital landscape.