During the outbreak of COVID-19 in Wuhan, the public used Weibo to acquire information, express emotions, and seek help at a historic and unprecedented scale. This situational information is valuable for authorities to initiate emergency policies and protect people’s health. Although event detection and situation awareness during COVID-19 using social media data have been investigated in recent studies, the spatiotemporal evolution patterns of social topics during COVID-19 at the community level are still limited. To address this limitation, this study developed a methodology to explore the dynamics of social topics under the influence of COVID-19 at a community level in Wuhan using geotagged Weibo posts. The disease-related topics exhibited the spatial variations in different urban communities and reflected the dynamics of public attention. Moreover, we used the reported COVID-19 case data in Wuhan and geotagged Weibo posts in Beijing to validate the effectiveness of the proposed methodology. These findings help to track social topic evolution at the community level and gain a better understanding of the spatial variations of public attention during urban emergencies.