Rochester researchers are mining Twitter to identify feelings and themes of the COVID-19 pandemic.
The University of Rochester computer science group found a few key themes by analyzing tweets. They created a process that “combines deep learning model scores with psychological textual features and users’ demographic information”.
Some of their key findings were:
- Significantly higher anxiety associated with hoarding-related tweets, which spiked in March and April.
- College students tended to be more preoccupied with COVID-19 issues that affected them personally, such as school closures and their home towns.
- New Yorkers were more likely to talk about impact COVID-19 had on hospitals. California and Florida Twitter users were more likely to comment on government policies related to COVID-19.