Combating Fake News Utilizing Content-Based Word Embedding and Language Features

The rapid growth of social media and online platforms has made disseminating false information a pressing concern. During the COVID-19 pandemic, there was an increase in the spread of false information, which caused confusion and panic and could be harmful to public health. As a result, researchers have focused their efforts on developing automated systems capable of detecting and preventing COVID-19 hoaxes. In the present research, 71 Language Features (LF) and content-based word embedding were used. The COVID-19 dataset’s properties were extracted and fed into machine learning classifiers for classification. We evaluated various models for the task and found that Adaboost outperformed all other models with 97.50% accuracy.