Forecasting Covid-19 Epidemic in Canada with Spatial-Temporal Models That Exploit Population Behaviour on Twitter

新冠肺炎疫情正在给公共卫生和世界经济造成前所未有的损害。能够准确预测新冠肺炎的传播对于加拿大联邦和省级政府制定最大限度地保护加拿大人生命安全和迅速重振加拿大经济的政策和措施至关重要。在这个项目中，我们的目标是通过利用推特上揭示的人口行为和病毒在加拿大传播的空间相关性，开发准确的人工智能启用的预测模型，用于预测和预测加拿大新冠肺炎疫情。本研究将现代机器学习和文本挖掘技术与流行病学建模相结合。该项目的成果是一套经过验证的模型、算法和网络应用程序，能够以显著高于迄今开发的所有已知模型和算法的精度预测加拿大各地每天的新冠肺炎新病例数量。 这项研究将对健康和社会经济产生深远的影响。例如，加拿大各级政府可能会积极制定应对新冠肺炎的政策和措施；各省的医疗系统可能会更好地规划和准备治疗新冠肺炎患者的医疗资源；各种规模的企业可能会利用疫情预测来设计更具弹性的商业战略和管理解决方案。

The Covid-19 pandemic is creating unprecedented damages to the public health and world economy. Being able to accurately forecast the spread of Covid-19 is critical for the federal and provincial governments of Canada to devise policies and measures maximally protecting the lives of Canadians and rapidly reviving the Canadian economy. In this project, we aim at developing accurate AI-enabled predictive models for the forecast and projection of Covid-19 epidemic in Canada by exploiting the population behaviour revealed on Twitter and the spatial correlation of the viral spread across Canada. Modern machine learning and text mining techniques will be combined with epidemiological modelling in this research. The outcome of this project is a validated suite of models, algorithms and web application that is able to forecast the daily number of new cases of Covid-19 across Canada at an accuracy significantly higher than all known models and algorithms developed to date. This research will have profound health and socio-economical impact. For example, the Canadian governments at various levels may proactively devise policies and measures to fight Covid-19; healthcare systems in all provinces may better plan and prepare medical resources for treating Covid-19 patients; business of all sizes may exploit the epidemic projections to design more resilient business strategies and managerial solutions.