ABSTRACT
Many nations of the world struggle with the COVID-19 pandemic, as the disease causes wide sweeping changes to society and the economy. One of the consequences of the pandemic is its effect on mental health stress. Gauging stress levels at scale is challenging to implement, as traditional methods require administrative labour and time. However, a combination of supervised Machine Learning (ML) and social media analytics could provide a faster and aggregated way to detect the stress levels of a population. This study investigates the potential clinical usage of ML practices for detecting stress in Twitter content, as a quantitative measure of stress at scale. The stress scores obtained by the models will be compared to the COVID-19 timeline of daily new cases. © 2023 ACM.