COVID-19 Fake News Detection via Graph Neural Networks in Social Media.

Recently it is convenient for people to seek out and consume news from social media, but misinformation including fake news and low-quality information also spreads which may have extremely negative impacts on individuals and society especially in the pandemics e.g., Covid-19. Previous fake news detectors view articles or tweets as i.i. d data and ignore the relation between them. In this paper we propose a novel fake news detection framework by exploring the similarity relation between tweets and mapping this problem into a semi-supervised classification task on a graph. We evaluate our proposed framework on a real-world social media dataset and the experimental results demonstrate the effectiveness of our proposed method comparing to different baselines.