The COVID-19 pandemic has affected populations worldwide, with extreme health, economic, social, and political implications. Health care professionals (HCPs) are at the core of pandemic response and are among the most crucial factors in maintaining coping capacities. Yet, they are also vulnerable to mental health effects caused by managing a long-lasting emergency with a lack of resources and under complicated personal concerns. However, there is a lack of longitudinal studies that investigate the HCP population. In this study, we analyze the state of mind of HCPs as expressed in online discussions published on Twitter before and during the COVID-19 pandemic.

The 53,063 Twitter profiles for this study were selected using an active learning process that iteratively uses machine learning and manual data labeling. We analyzed the topics and emotions in their discourses during 2020 and correlated them with the pandemic development. We have also modeled the language dynamics by fine-tuning the BERT transformer to HCP tweets in a three-month sliding window. Trust in health organizations was quantified using the Word Embedding Asociation Test. The trust of HCPs in CDC, USFDA, and WHO declined until August 2020 and increased back to the previous levels by the end of 2020. In general, professional topics accounted for 44.5% of tweets by HCPs from January 1, 2019, to December 6, 2020. The levels of joy and sadness exceeded their minimal and maximal values from 2019, respectively, 80% of the time (P=.001). Most interestingly, fear preceded the pandemic waves, in terms of the differences in confirmed cases, by 2 weeks with a Spearman correlation coefficient of ρ(47 pairs)=0.340 (P=.03). The revealed emotional trends indicate the utmost importance of providing emotional support for HCPs to prevent fatigue, burnout, and mental health disorders during the post-pandemic period.

In collaboration with Aviad Elyashar, Ilia Plochotnikov, Idan-Chaim Cohen, and Odeya Cohen from the Ben-Gurion University of the Negev.

Bio: Dr Rami Puzis is a senior lecturer (Assistant Prof.) at the Department of Software and Information Systems Engineering at Ben-Gurion University. Rami has graduated BSc in Software Engineering and MSc and PhD in Information Systems Engineering. Rami was a post-doctoral research associate in the Lab for Computational Cultural Dynamics, University of Maryland. His main research interests include network analysis with applications to security, social networks, computer communication, and biology. Over the past years, Rami has managed research projects funded by Deutsche Telekom AG, Israeli Ministry of Defense, Israeli Ministry of Trade and Commerce, and leading industries in Israel. His recent research projects focused on Web Intelligence, Security Awareness, Social Networks Analysis, etc.