Depression in the Times of COVID-19 - A Machine Learning Analysis Based on the Profile of Mood States

Aug 6, 2026

Upload by Jiven

As the COVID-19 pandemic unfolds, fear and depression spread in parallel, undermining well-being among the general public and health care workers. To accelerate mental health diagnosis, the study applies emotion analysis and recognition to mine opinions at scale. A machine learning classifier is developed to identify depression, one of the moods most associated with COVID-19. Using two Twitter datasets from 2020 and 2022, the research tracks how mood and emotion signals change over time and supports well-being-related strategic choices for the UK and globally.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Introduction

Background on COVID-19 and mental health

Motivation and long-term goal

Data collection and scope

School of Engineering, Computing and Mathematics Faculty of Science and Engineering 2023-04-21 Depression in the Times of COVID-19: A Machine Learning Analysis Based on the Profile of Mood States M Palomino R Allen AP Varma Let us know how access to this document benefits you General rights All content in PEARL is protected by copyright law. Author manuscripts are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author. Take down policy If you believe that this document breaches copyright please contact the library providing details, and we will remove access to the work immediately and investigate your claim. Follow this and additional works at: [https://pearl.plymouth.ac.uk/secam-research](https://pearl.plymouth.ac.uk/secam-research) 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: 10. 14746/ amup.9788323241775 This Conference Proceeding is brought to you for free and open access by the Faculty of Science and Engineering at PEARL. It has been accepted for inclusion in School of Engineering, Computing and Mathematics by an authorized administrator of PEARL. For more information, [please contact](please contact openresearch@plymouth.ac.uk)[ openresearch@plymouth.ac.uk](please contact openresearch@plymouth.ac.uk). University of Plymouth PEARL [https://pearl.plymouth.ac.uk](https://pearl.plymouth.ac.uk) | Faculty of Science and Engineering | School of Engineering, Computing and Mathematics | | --- | --- | 2023-04-21 Depression in the Times of COVID-19: A Machine Learning Analysis Based on the Profile of Mood States Palomino, M [https://pearl.plymouth.ac.uk/handle/10026.1/20774](https://pearl.plymouth.ac.uk/handle/10026.1/20774) 10.14746/amup.9788323241775 Adam Mickiewicz University Press All content in PEARL is protected by copyright law. Author manuscripts are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author. Depression in the Times of COVID-19: A Machine Learning Analysis Based on the Profile of Mood States Marco A. Palomino∗ , Rohan Allen∗ , Aditya Padmanabhan Varma† ∗ School of Engineering, Computing and Mathematics (SECaM), University of Plymouth [marco.palomino@plymouth.ac.uk](marco.palomino@plymouth.ac.uk); [rohan.allen-13@students.plymouth.ac.uk](rohan.allen-13@students.plymouth.ac.uk) †Department of Computer Science and Engineering, Chalmers University of Technology [vaditya@chalmers.se](vaditya@chalmers.se) 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-

FAQs

What mental health task does the study focus on during the COVID-19 pandemic?

The study focuses on identifying depression using emotion analysis and recognition techniques to support faster mental health diagnosis.

How do the authors analyze changes in public discourse over time?

They gather two Twitter collections, one from 2020 and another from 2022, and compare how conveyed moods and emotions evolve across the two-year span.

What main approach and tool does the paper propose?

It proposes a machine learning classifier designed to identify depression, a mood commonly associated with COVID-19.

Aug 6, 2026

Upload by Jiven