Abstract: False information concerning topics or events, such as COVID-19, is referred to as fake news. Social media juggernauts claimed to take COVID-19-related falsehoods seriously at the same time, yet they were ineffective. Real news data are gathered for this study via information fusion from websites related to news broadcasting, health, and the government, whereas false news data are gathered from social media platforms. Using cutting-edge deep learning models, 39 features were extracted from multimedia texts and utilised to identify bogus news about COVID-19. The accuracy of our model's false news feature extraction increased from 59.20 to 86.12 percent. Our best recall and F1-Measure for fake news were 83% utilising the Gated Recurrent Units (GRU) model, which has an overall high precision of 85%. Similarly, F1-Measure for real, recall, and precision
Keywords: Fake news, Social media, Deep learning, NLP, Mining Emotions
|
DOI:
10.17148/IJARCCE.2023.12242
