Deploying Artificial Intelligence to Combat Covid-19 Misinformation on Social Media: Technological and Ethical Considerations

This paper reports on AI research into online misinformation pertaining to the COVID-19 pandemic within the Canadian context. This is part of our longer-term goal, i.e., development of a machine-learning tool to assist social media platforms, online service providers and government agencies in identifying and responding to misinformation on social media. We report on predictive accuracies accomplished by applying a combination of technologies, including a custom-designed web- crawler, The Dark Crawler, the Posit toolkit, and four different machine-learning models based on Naive Bayes, Support Vector Machines, LibLinear and LibShortText. Overall, we found that Posit and LibShortText models showed higher levels of correlation to the pre-determined (manual and machine-driven) data classifications than the other machine-learning algorithms tested. We further argue that the harms associated with COVID-19 misinformation - e.g., the social and economic damage, and the deaths and severe illnesses - outweigh the right to personal privacy and freedom of speech considerations.