Reconstructing decision-making dynamics during public health crises by applying data science to public records

Area of Science:

• Public Health
• Data Science
• Political Science

Background:

• Public health policies significantly influence government responses to crises.
• The dynamics linking policies to outcomes are often obscured by social networks, power imbalances, and political factors.
• Intergovernmental communications are key to understanding these hidden dynamics but are difficult to access and analyze.

Purpose of the Study:

• To demonstrate how data science tools can overcome challenges in analyzing large-scale communication datasets.
• To reconstruct decision-making processes during a public health crisis.
• To provide insights for improving future public health policy and response.

Main Methods:

• Utilized free and open-source data science tools.
• Mined a large image dataset of intergovernmental communications.
• Reconstructed decision-making pathways during the Flint Water Crisis.

Main Results:

• Successfully applied data science techniques to analyze complex communication data.
• Visualized and reconstructed the decision-making process during the Flint Water Crisis.
• Highlighted the practical application of data science in uncovering hidden factors in public health policy implementation.

Conclusions:

• Data science offers powerful methods for analyzing previously inaccessible information.
• Understanding hidden dynamics is crucial for effective public health policy and crisis response.
• The Flint Water Crisis case study demonstrates the potential for improved policy through data-driven insights.