Back

Sentiment analysis of employees and COVID-19 vaccine hesitancy at workplace

Akpan, I. J.; Warner, T.; Peter, M.

2025-02-03 public and global health
10.1101/2025.01.30.25321414 medRxiv
Show abstract

Vaccination is a potent means to combat the spread of infectious disease epidemics or pandemics, such as the COVID-19 pandemic. However, getting sufficient people to accept the vaccine and achieve herd immunity remains a significant challenge. This study evaluates preschool workers sentiments and challenges during in-person schooling amidst the COVID-19 pandemic and attitudes toward COVID-19 vaccination through a survey. The study surveyed preschool workers as part of a consulting project. Workers sentiments are analyzed using Azure Machine Learning (AML) data analytic method, statistical analysis, and theoretical evaluation. The results show that no association exists between employee job category (teachers versus support staff) and COVID-19 vaccine hesitancy. However, fewer teaching staff were hesitant to take the COVID-19 vaccine than the support staff (46% < 50%), but the difference was not significant [Chi-Square ({chi}2) = 0.009; p>0.05]. The overall sentiments of all preschool workers showed 46%, indicating low neutrality, implying hesitancy toward the COVID-19 vaccine. Preschool workers who felt optimistic about the vaccines potency cited scientific reasons; those with neutral sentiments needed further information and assurances about the side effects, indicating that appropriate health education can sway more people positively towards accepting the vaccine; people with negative sentiments displayed distrust, fear, personal beliefs, and misinformation. The results also highlight the need to educate all workers on vaccine potency despite the levels of education. Regardless of academic qualifications, any uninformed person can fall prey to misinformation and conspiracy theories. Proper health education helps people make informed decisions.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.