Predicting the issuance of COVID-19 stay-at-home orders in Africa: Using machine learning to develop insight for health policy research

During the COVID-19 pandemic, many countries have issued stay-at-home orders (SAHOs) to reduce viral transmission. Because of their social and economic consequences, SAHOs are a politically risky decision for governments. Researchers typically attribute public health policymaking to five theoretically significant factors: political, scientific, social, economic, and external. However, a narrow focus on extant theory runs the risk of biasing findings and missing novel insights. This research employs machine learning to shift the focus from theory to data to generate hypotheses and insights "born from the data” and unconstrained by current knowledge. Beneficially, this approach can also confirm the extant theory. We apply machine learning in the form of a random forest classifier to a novel and multiple-domain data set of 88 variables to identify the most significant predictors of the issuance of a COVID-19-related SAHO in African countries (n = 54). Our data set includes a wide range of variables from sources such as the World Health Organization that cover the five principal theoretical factors and previously ignored domains. Generated using 1000 simulations, our model identifies a combination of theoretically significant and novel variables as the most important to the issuance of a SAHO and has a predictive accuracy using 10 variables of 78%, which represents a 56% increase in accuracy compared to simply predicting the modal outcome.

Predicting the issuance of COVID-19 stay-at-home orders in Africa: Using machine learning to develop insight for health policy research.

During the COVID-19 pandemic, many countries have issued stay-at-home orders (SAHOs) to reduce viral transmission. Because of their social and economic consequences, SAHOs are a politically risky decision for governments. Researchers typically attribute public health policymaking to five theoretically significant factors: political, scientific, social, economic, and external. However, a narrow focus on extant theory runs the risk of biasing findings and missing novel insights. This research employs machine learning to shift the focus from theory to data to generate hypotheses and insights "born from the data" and unconstrained by current knowledge. Beneficially, this approach can also confirm the extant theory. We apply machine learning in the form of a random forest classifier to a novel and multiple-domain data set of 88 variables to identify the most significant predictors of the issuance of a COVID-19-related SAHO in African countries (n = 54). Our data set includes a wide range of variables from sources such as the World Health Organization that cover the five principal theoretical factors and previously ignored domains. Generated using 1000 simulations, our model identifies a combination of theoretically significant and novel variables as the most important to the issuance of a SAHO and has a predictive accuracy using 10 variables of 78%, which represents a 56% increase in accuracy compared to simply predicting the modal outcome.

Psychophysiology, cognition, and political differences: Guest editors' introduction to the special issue.

We introduce the Politics and the Life Sciences special issue on Psychophysiology, Cognition, and Political Differences. This issue represents the second special issue funded by the Association for Politics and the Life Sciences that adheres to the Open Science Framework for registered reports (RR). Here pre-analysis plans (PAPs) are peer-reviewed and given in-principle acceptance (IPA) prior to data being collected and/or analyzed, and are published contingent upon the preregistration of the study being followed as proposed. Bound by a common theme of the importance of incorporating psychophysiological perspectives into the study of politics, broadly defined, the articles in this special issue feature a unique set of research questions and methodologies. In the following, we summarize the findings, discuss the innovations produced by this research, and highlight the importance of open science for the future of political science research.

A Novel Network Approach to Capture Cognition and Affect: COVID-19 Experiences in Canada and Germany.

We tested a novel method for studying human experience (thoughts and affect). We utilized Cognitive-Affective Maps (CAMs)-an approach to visually represent thoughts and their affective connotations as networks of concepts that individuals associate with a given event. Using an innovative software tool, we recruited a comparative sample of (n = 93) Canadians and (n = 100) Germans to draw a CAM of their experience (events, thoughts, feelings) with the Covid-19 pandemic. We treated these CAM networks as a series of directed graphs and examined the extent to which their structural properties (latent and emotional) are predictive for the perceived coronavirus threat (PCT). Across multiple models, we found consistent and significant relationships between these network variables and the PCT in both the Canadian and German sample. Our results provide unique insights into individuals' thinking and perceptions of the viral outbreak. Our results also demonstrate that a network analysis of CAMs' properties is a promising method to study the relationship between human thought and affective connotation. We suggest that CAMs can bridge several gaps between qualitative and quantitative methods. Unlike when using quantitative tools (e.g., questionnaires), participants' answers are not restricted by response items as participants are free to incorporate any thoughts and feelings on the given topic. Furthermore, as compared to traditional qualitative measures, such as structured interviews, the CAM technique may better enable researchers to objectively assess and integrate the substance of a shared experience for large samples of participants.