This study aims (1) to evaluate the feasibility and accuracy of using open-source data for monitoring COVID-19 and (2) to estimate demographic-specific excess mortality from all causes in 2020 and 2021 using official death records and obituary data. Automated data collection from text mining of openly available online obituaries could allow us to derive quick estimates of the age, sex, and race distribution of deaths by location in a cost-effective way, which is currently not possible since federal available datasets do not offer the necessary granularity or timeliness needed for monitoring efforts that can inform policy. The approaches this study will pursue will also help prepare tools to monitor future outbreaks and understand other types of causes of death, e.g., AIDS or opioid overdose.
