911 4 COVID-19: Analyzing Impact of COVID-19 on 911 Call Behavior

This paper explores the impact of COVID-19 on 911 Call behavior to help first responders develop effective solutions to emergent situations proactively. Correct prediction of call volume and call type helps first responders optimize resource allocation. We used time series regression to explore the relationship between the number of COVID-19 cases, weather, and stay-at-home orders using 911 Call records in New Hanover County, North Carolina, USA. We divided 911 calls into six categories: breathing, domestic violence, injury, psychiatric, traffic, and violence-related calls. We observed a positive correlation between the number of COVID-19 cases and the number of 911 calls in all categories except domestic violence. We also developed a Bayesian regression prediction model to forecast the number of 911 calls given the number of COVID-19 cases. Our model excelled regarding domestic violence and total calls, and achieved satisfactory results for traffic and violence calls. To our knowledge, there is no prior relevant work, so we were unable to compare our results with other models.