A cooperative deep learning model for fake news detection in online social networks

Fake news, which considers and modifies facts for virality objectives, causes a lot of havoc on social media. It spreads faster than real news and produces a slew of issues, including disinformation, misunderstanding, and misdirection in the minds of readers. To combat the spread of fake news, detection algorithms are used, which examine news articles through temporal language processing. The lack of human engagement during fake news detection is the main problem with these systems. To address this problem, this paper presents a cooperative deep learning-based fake news detection model.The suggested technique uses user feedbacks to estimate news trust levels, and news ranking is determined based on these values. Lower-ranked news is preserved for language processing to ensure its validity, while higher-ranked content is recognized as genuine news. A convolutional neural network (CNN) is utilized to turn user feedback into rankings in the deep learning layer. Negatively rated news is sent back into the system to train the CNN model. The suggested model is found to have a 98% accuracy rate for detecting fake news, which is greater than most existing language processing based models.The suggested deep learning cooperative model is also compared to state-of-the-art methods in terms of precision, recall, F-measure, and area under the curve (AUC). Based on this analysis, the suggested model is found to be highly efficient. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.