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

利用 Twitter 上人群行为的时空模型预测加拿大的 Covid-19 疫情

• 批准号: 550139-2020
• 负责人: Mao, Yongyi
• 金额: $ 3.64万
• 依托单位: University of Ottawa
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=701544
• 关键词: Forecasting; Covid; 19; Epidemic; Canada

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.

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Covid-19的传播对于加拿大联邦和省政府制定最大限度地保护加拿大人的生命和迅速恢复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加拿大各地病毒传播的空间相关性，开发准确的人工智能预测模型，以预测和预测加拿大的Covid-19疫情。在本研究中，现代机器学习和文本挖掘技术将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web应用程序，能够预测加拿大每天新冠肺炎病例的数量，其准确性远远高于迄今为止开发的所有已知模型和算法。