Close

We use cookies to improve your experience of our website. Privacy Policy

Skip to main content

Institute of Applied Data Science

Search
Menu

News

Investigating mental and physical disorders associated with COVID-19 in online health forums

7 January 2021

Professor Conrad Bessant
Professor Conrad Bessant

Queen Mary Turing Fellows: Dr Fabrizio Smeraldi from School of Electronic Engineering and Computer Science and Professor Conrad Bessant from School of Biological and Chemical Sciences have recently published an article on their study investigating the mental and physical disorder associated with COVID-19 in online health forums.

The study, co-led by Dr Maryam Abdollahyan from School of Biological and Chemical Sciences and colleagues from King's College London, provides an in-depth data extraction and Natural Language Processing - based analysis on the evolution of mental and physical health concerns relating to the COVID-19 pandemic among online health forum users.

Online health forums provide rich and untapped real-time data on population health. Through novel data extraction and natural language processing (NLP) techniques, we characterise the evolution of mental and physical health concerns relating to the COVID-19 pandemic among online health forum users.

Data from 739,434 posts by 53,134 unique users of three leading online health forums: HealthBoards, Inspire and HealthUnlocked, from the period 1st January 2020 to 31st May 2020 was obtained. Using NLP, researchers analysed the content of posts related to COVID-19.

Primary outcome measures included: the proportion of forum posts containing COVID-19 keywords, proportion of forum users making their very first post about COVID-19, and a number of COVID-19 related posts containing content related to physical and mental health comorbidities.

Posts discussing COVID-19 and related comorbid disorders spiked in early- to mid-March around the time of global implementation of lockdowns prompting a large number of users to post on online health forums for the first time. The pandemic and corresponding public response has had a significant impact on posters' queries regarding mental health.

Researchers demonstrated that it is feasible to characterise the content of online health forum user posts regarding COVID-19 and measure changes over time. Social media data sources such as online health forums can be harnessed to strengthen population-level mental health surveillance.

More about the study here.

Link: https://www.medrxiv.org/content/10.1101/2020.12.14.20248155v...

Updated by: Michal Filus