Depression in the Times of COVID-19: A Machine Learning Analysis Based on the Profile of Mood States
Abstract
As the COVID-19 pandemic continues to unfold, a parallel outbreak of fear and depression is also spreading around, impacting negatively on the well-being of the general public and health care workers alike. In an attempt to develop tools to expedite mental health diagnosis, we have looked into emotion analysis and recognition, as this has become indispensable to understand and mine opinions. We have produced a machine learning classifier capable of identifying one of the moods most commonly associated with COVID-19: depression. To analyse how moods and emotions conveyed about COVID-19 have changed in the public discourse over time, we have gathered two Twitter collections—one from 2020 and one from 2022. Our initial findings indicate that fear and depression remain attached to the COVID-19 discourse over the span of two years. Our insights can aid the design of strategic choices concerning the well-being of people in the UK and worldwide.
DOI
10.14746/amup.9788323241775
Publication Date
2023-04-21
Event
10th Language and Technology Conference
Publisher
Adam Mickiewicz University Press
ISBN
978-83-232-4177-5
Embargo Period
2024-11-22
Recommended Citation
Palomino, M., Allen, R., & Varma, A. (2023) 'Depression in the Times of COVID-19: A Machine Learning Analysis Based on the Profile of Mood States', Adam Mickiewicz University Press: Available at: https://doi.org/10.14746/amup.9788323241775
