• M.D.Amala Dhaya
• A.Shakeela Joy
• A.Jackulin Jeba
• M.Mary Naveena
• A.Micheal Vibisha

Fake news has become widespread on online social networks, affecting offline society. To improve trustworthiness, researchers are investigating methods and algorithms for detecting fake news articles, creators, and subjects. A novel gated graph neural network, FAKEDETECTOR, is introduced to learn representations of news articles, creators, and subjects simultaneously. Experiments on a real-world fake news dataset compare FAKEDETECTOR with state-of-the- art models. Studying fake news detection on online social networks using heterogeneous information sources and credibility inference, aiming to identify fake news simultaneously. Real fake news has higher credibility, while unauthentic fake news has lower credibility. This project supports machine learning's potential for classifying fake news, excluding "give away" topic words in training sets. It can pick up trigrams on less specific topics, making it a promising tool for augmenting human detection of fake news.Fake news emerged in the web age, primarily to increase readership and mental health. The research project aims to develop a fake news detection model using Text Victimizer and machine learning techniques. The model's accuracy is greater than 97.87%. using TF-IDF and Passive-Aggressive Classifier

ML. fake news, deep learning

"https://www.jetir.org/submit-paper-phase2.php", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.k221-k229, June-2023, Available :http://www.jetir.org/papers/JETIR2306A27.pdf

"https://www.jetir.org/submit-paper-phase2.php", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. ppk221-k229, June-2023, Available at : http://www.jetir.org/papers/JETIR2306A27.pdf