SBIR Phase I (COVID-19): Identifying Medical Supply Shortages on Social Media for Fast and Effective Disaster Response

这项小企业创新研究（SBIR）第一阶段项目的更广泛影响包括在COVID-19危机期间通过确定医疗服务提供者的需求并为政府机构和医疗设备供应商和制造商编写报告提供即时帮助。拟议的自然语言处理方法将帮助(1)医院和诊所寻找医疗用品、个人防护设备和测试用品，以满足他们的需求；(2)政府协调应对；(3)制造商和供应商寻求有关需求的信息。此外，它还可用于查明其他非医疗用品短缺情况，并可加以调整，以对其他灾害或疫情作出有效反应。这个小企业创新研究（SBIR）第一阶段项目将利用自然语言处理和机器学习方面的最新进展，根据从社交媒体中的自由文本中获得的见解，确定医疗设备和用品的大规模需求，并将这些需求转换为集中的、易于访问的结构化数据格式。该技术将识别社交媒体上的需求表达；识别用户、他们的具体需求和地点；并生成按地理位置排序的可操作格式化列表。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact of this Small Business Innovation Research (SBIR) Phase I project consists of providing immediate help during the COVID-19 crisis by identifying the needs of medical providers and compiling reports for government agencies and medical equipment suppliers and manufacturers. The proposed Natural Language Processing methodology will help (1) hospitals and clinics seeking medical supplies, personal protective equipment, and testing supplies to meet their needs; (2) the government coordinating response; (3) manufacturers and suppliers seeking information regarding needs. Additionally, it can be used to identify other non-medical supply shortages and can be adapted to provide an efficient response for other disasters or outbreaks.This Small Business Innovation Research (SBIR) Phase I project will leverage recent advances in natural language processing and machine learning to identify at scale needs in medical equipment and supplies, based on insights derived from free text in social media, and convert these needs into a centralized, easily accessible structured data format. The technology will identify expressions of needs on social media; identify users, their specific needs, and locations; and generate geographically sorted actionable formatted lists.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.