A short summary of the project’s aims:

Governments continually formulate policies and seek feedback from the public on their impacts to aid in policy refinement. For instance for crises such as the pandemic, policymakers need tools that can assess policy impacts on the public in near real-time. Particularly, containment policies during the Covid-19 pandemic affected people’s well-being, yet changes in public emotions and sentiments are challenging to assess. Our work proposes a solution by analyzing social media posts to compute salient concerns and daily public sentiment values as a proxy of public well-being. We do so by combining multiple methods such as multiple liner regression, regression discontinuity in time, and state-of-art natural language processing techniques. This approach can provide key benefits of using a data-driven approach to identify public concerns and provide near real-time assessment of policy impacts by computing public sentiment and concerns based on postings on social media. Our goal is to generalize the technique to other policy scenarios and incorporate it into the policy formulation and refinement cycle.