Causal Investigation of Public Opinion during the COVID-19 Pandemic via Social Media Text

Understanding the needs and fears of citizens, especially during a pandemic such as COVID-19, is essential for any government or legislative entity. An effective COVID-19 strategy further requires that the public understand and accept the restriction plans imposed by these entities. In this paper, we explore a causal mediation scenario in which we want to emphasize the use of NLP methods in combination with methods from economics and social sciences. Based on sentiment analysis of Tweets towards the current COVID-19 situation in the UK and Sweden, we conduct several causal inference experiments and attempt to decouple the effect of government restrictions on mobility behavior from the effect that occurs due to public perception of the COVID-19 strategy in a country. To avoid biased results we control for valid country specific epidemiological and time-varying confounders. Comprehensive experiments show that not all changes in mobility are caused by countries implemented policies but also by the support of individuals in the fight against this pandemic. We find that social media texts are an important source to capture citizens' concerns and trust in policy makers and are suitable to evaluate the success of government policies. © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.

Burnout among Nursing Workers Who Provide Nursing Care for People Infected with COVID-19

Background: The unpredictable nature of the new COVID-19 pandemic and what is already troubling incidents of affecting nursing workers can have a significant impact on their psychological well-being. Objective: To describe the prevalence of burnout among nursing personnel caring for patients with COVID-19 and associated factors. Study Design: cross-sectional study. Setting: Alhossien Teaching Hospitals designated to isolate patients with COVID-19 in Thi Qar Governorate. Participants: A sample of 50 nurses practitioners in the study sites who were caring for COVID- 19 patients. Measurements: age, gender, marital status, job title, certificate, job category, number of years of service, working period, hospitalization, and work load, as well as burnout level in each subscale consist (12)items. Results: Nurses working in isolation hospitals suffer from high levels of burnout, emotional exhaustion, depersonalization, and personal underachievement. Limitations: There was no control group and therefore we cannot claim a causal relationship between COVID-19 and the level of fatigue observed. Not all confounders may have been accounted for. Conclusions: Burnout is prevalent among nurses caring for COVID-19 patients. Age, gender, job category, and location of practice contribute to the level of burnout experienced by nurses. Recommendations: Psychologically rehabilitate nursing workers under the supervision of specialists and give them financial and moral rewards to compensate for the harm they have suffered. © 2022 IEEE.

Assessing the Causal Impact of COVID-19 Related Policies on Outbreak Dynamics: A Case Study in the US

Analyzing the causal impact of different policies in reducing the spread of COVID-19 is of critical importance. The main challenge here is the existence of unobserved confounders (e.g., vigilance of residents) which influence both the presence of policies and the spread of COVID-19. Besides, as the confounders may be time-varying, it is even more difficult to capture them. Fortunately, the increasing prevalence of web data from various online applications provides an important resource of time-varying observational data, and enhances the opportunity to capture the confounders from them, e.g., the vigilance of residents over time can be reflected by the popularity of Google searches about COVID-19 at different time periods. In this paper, we study the problem of assessing the causal effects of different COVID-19 related policies on the outbreak dynamics in different counties at any given time period. To this end, we integrate COVID-19 related observational data covering different U.S. counties over time, and then develop a neural network based causal effect estimation framework which learns the representations of time-varying (unobserved) confounders from the observational data. Experimental results indicate the effectiveness of our proposed framework in quantifying the causal impact of policies at different granularities, ranging from a category of policies with a certain goal to a specific policy type. Compared with baseline methods, our assessment of policies is more consistent with existing epidemiological studies of COVID-19. Besides, our assessment also provides insights for future policy-making. © 2022 ACM.

Discovery of a Generalization Gap of Convolutional Neural Networks on COVID-19 X-Rays Classification.

A number of recent papers have shown experimental evidence that suggests it is possible to build highly accurate deep neural network models to detect COVID-19 from chest X-ray images. In this paper, we show that good generalization to unseen sources has not been achieved. Experiments with richer data sets than have previously been used show models have high accuracy on seen sources, but poor accuracy on unseen sources. The reason for the disparity is that the convolutional neural network model, which learns features, can focus on differences in X-ray machines or in positioning within the machines, for example. Any feature that a person would clearly rule out is called a confounding feature. Some of the models were trained on COVID-19 image data taken from publications, which may be different than raw images. Some data sets were of pediatric cases with pneumonia where COVID-19 chest X-rays are almost exclusively from adults, so lung size becomes a spurious feature that can be exploited. In this work, we have eliminated many confounding features by working with as close to raw data as possible. Still, deep learned models may leverage source specific confounders to differentiate COVID-19 from pneumonia preventing generalizing to new data sources (i.e. external sites). Our models have achieved an AUC of 1.00 on seen data sources but in the worst case only scored an AUC of 0.38 on unseen ones. This indicates that such models need further assessment/development before they can be broadly clinically deployed. An example of fine-tuning to improve performance at a new site is given.