Amid the social restrictions and quarantine policies imposed during the global spread of COVID-19, human mobility patterns changed dramatically. To better understand the relationships between human mobility, government policies and cases of COVID-19, U.S. researchers have developed an interactive web application that illustrates the connections between human mobility, government policies, and cases of COVID-19.
The app was built with data from three independent sources: a map, which provides data on human movement via walking, driving and public transportation; COVID-19 Government Response Tracker, which provides data on government policies implemented during the pandemic; and global cases of COVID-19. Users can select a specific state or county in the U.S. as well as another country and see how mobility and COVID-19 cases changed over time or in response to government policies or social circumstances.
At a macro level, understanding movement patterns of people can help influence decision making for higher-level policies, like social gathering restrictions, mask recommendations, and tracking and tracing the spread of infectious diseases. At a local level, understanding the movement of people can lead to more specific decisions, like where to set up testing sites or vaccination sites.
Since the initial launch, the researchers have continued to update the application with appropriate data at regular intervals. The web application produces interesting visualisations that can reveal fascinating trends specific to a given area that might otherwise not be recognised.
During their exploration of the data, the researchers found a handful of case studies that suggested interesting trends. For example, in New Orleans, the application shows a spike in human mobility at the end of February 2020, which coincided with Mardi Gras celebrations. Coincidentally, there was a corresponding spike in COVID-19 cases almost a month after the event.
Although the application is specific to the pandemic, the framework could be modified rather easily to create a similar application for natural disasters as long as appropriate data sets are available. Understanding historic mobility patterns are needed for policymakers to make informed decisions regarding transportation systems and other areas both under normal circumstances and in response to extreme events like a pandemic or a natural disaster.
According to a page, this data shows the number of COVID-19-related policy responses taken by the government on a given day. Indicators include containment and closure policies such as school closures, workplace closures, public event cancellations, restrictions on gatherings, public transportation closures, stay at home requirements, restrictions on internal movement, and international travel controls. Other indicators include health system policies such as public information campaigns, testing policies, contact tracing, and facial covering policies.
Other U.S. researchers have also been using data by an online tool to provide insights into people’s online behaviour, specifically people’s response to COVID-19. As reported by OpenGov Asia, A research project funded by the National Science Foundation (NSF) develops an online tool called CitizenHelper. This tool can sort through millions of tweets to identify behaviours that could assist emergency agencies and give them an understanding of the population’s attitudes. The tool uses artificial intelligence (AI) techniques to filter the posts and then determine the relevance and information level of each tweet.
The tool helps these researchers to scale work that would be difficult for humans to do alone. The head of the research team says that humans are good at contextual understanding to filter content but they cannot scale. Machines, on the other hand, are good at scaling, but they do not deeply understand the context very well. Hence, a human-AI teaming approach is invaluable. The algorithms need humans to help them improve their accuracy. CitizenHelper allows this very seamless interactive mechanism for humans and computers. The humans can provide feedback to the machine on what the machine has predicted.