Navigation auf


Department of Geography

Capturing mood and affective states via Twitter

The coronavirus primarily affects our bodies, but it also has massive impact on our mental health. GIUZ researchers use Twitter content to detect emotional stress related to the COVID-19 pandemic across space and time. 

SoHo, Manhattan, New York
Photo: Unsplash (Yoav Aziz)

Together with an interdisciplinary research team, Tamar Edry and Oliver Gruebner analysed a large, anonymised dataset of tweets that were geo-tagged. From this, they developed a tool that maps geographic clusters of negative emotions over time, in line with the spread of the COVID-19 pandemic. Automated activities - especially "bot" accounts - were filtered out. 

With this innovative approach, spatial hotspots of emotional stress can be monitored in real-time and made accessible in interactive maps over time. This could be helpful for governments, NGOs, health experts and other stakeholders in order to specifically prepare measures in those regions where they are most urgently needed.

Geographic variation of emotional stress in Twitter tweets during COVID-19

The web-based geo-visualisation tool allows users to toggle between specific identified emotions or negative emotions in general, and to identify the extent to which bot accounts are the source of these emotions.

Edry, T., Maani, N., Sykora, M., Elayan, S., Hswen, Y., Wolf, M., Rinaldi, F., Galea, S., & Gruebner, O. (2021). Real-time geospatial surveillance of localized emotional stress responses to COVID-19: A proof of concept analysis. Health & Place, 70, 102598

Weiterführende Informationen


Dr. Oliver Grübner

Geographic Information Visualization and Analysis

Department of Geography, UZH

Phone: +41 44 635 51 52