The world is striving its best to survive the pandemic known as COVID-19. The problems and concerns surrounding the disease are not just that of virus novelty, health issues, death rate, and contagion but also mental health issues and the growing panic. Misinformation about the virus and its impact, cures, precautions, etc. are spreading as fast as (if not faster) the virus itself. It is of paramount importance that the general public and the frontline healthcare workers are equipped with the correct and updated information. While misinformation in the digital age is not a new concept, it becomes unnerving when the consequences include worldwide panic.
The concern addressed with this project is the ubiquity of misinformation. With so much information available around us, and the amount of overlap between the information reported by various sources makes it difficult to discern misinformation from actual data. There is hardly any rule or legislation in place to safeguard people against the spread of misinformation. Twitter is one of the social media giants bursting with news and information about the disease every day. As of April 14, 2020, the number of tweets on COVID-19 is 508,849,474 (Twitter Binder Blog, 2020).
There is no labelled dataset available that discerns fake vs real information about the disease.
People are unaware of the amount of misinformation they are consuming on a daily basis.
People need to approach new information with some level of skepticism, in the digital era.