α-Satellite Benchmark Datasets

α-Satellite数据集是由凯斯西储大学计算机与数据科学系开发的，用于支持AI驱动的系统进行分层社区级风险评估，以帮助抗击COVID-19。该数据集包含四个子集：疾病相关数据、人口统计和流动性数据、社交媒体数据以及构建的异构信息网络。数据集通过多种来源收集，包括官方公共卫生组织、数字媒体、社交媒体等，旨在提供实时大范围的疫情相关数据。创建过程涉及数据爬取、预处理和高级AI技术的应用。该数据集主要用于支持社区级风险评估，帮助制定有效的社区缓解策略，以应对快速演变的COVID-19疫情。The α-Satellite Dataset was developed by the Department of Computer and Data Sciences, Case Western Reserve University, to support AI-powered systems in conducting hierarchical community-level risk assessment for combating COVID-19. This dataset comprises four subsets: disease-related data, demographic and mobility data, social media data, and constructed heterogeneous information networks. It is collected from multiple sources including official public health organizations, digital media, social media and other channels, aiming to provide real-time and large-scale epidemic-related data. The dataset creation process involves data crawling, preprocessing, and the application of advanced AI technologies. It is primarily used to support community-level risk assessment and help formulate effective community mitigation strategies to address the rapidly evolving COVID-19 pandemic.