Modeling Spatiotemporal Pattern of Depressive Symptoms Caused by COVID-19 Using Social Media Data Mining

Abstract

By 29 May 2020, the coronavirus disease (COVID-19) caused by SARS-CoV-2 had spread to 188 countries, infecting more than 5.9 million people, and causing 361,249 deaths. Governments issued travel restrictions, gatherings of institutions were cancelled, and citizens were ordered to socially distance themselves in an effort to limit the spread of the virus. Fear of being infected by the virus and panic over job losses and missed education opportunities have increased people’s stress levels. Psychological studies using traditional surveys are time-consuming and contain cognitive and sampling biases, and therefore cannot be used to build large datasets for a real-time depression analysis. In this article, we propose a CorExQ9 algorithm that integrates a Correlation Explanation (CorEx) learning algorithm and clinical Patient Health Questionnaire (PHQ) lexicon to detect COVID-19 related stress symptoms at a spatiotemporal scale in the United States. The proposed algorithm overcomes the common limitations of traditional topic detection models and minimizes the ambiguity that is caused by human interventions in social media data mining. The results show a strong correlation between stress symptoms and the number of increased COVID-19 cases for major U.S. cities such as Chicago, San Francisco, Seattle, New York, and Miami. The results also show that people’s risk perception is sensitive to the release of COVID-19 related public news and media messages. Between January and March, fear of infection and unpredictability of the virus caused widespread panic and people began stockpiling supplies, but later in April, concerns shifted as financial worries in western and eastern coastal areas of the U.S. left people uncertain of the long-term effects of COVID-19 on their lives.

Stress-related emotional and behavioural impact following the first COVID-19 outbreak peak

“…Overall, these correlations may demonstrate our questionnaire’s sensitivity in capturing stress-related effects of COVID-19 in real-time. Interestingly, a similar correlation between stress symptoms (assessed by social media data mining) and the number of new COVID-19 cases was also found in a study in the United States 16 .…”

COVID-19: Detecting Government Pandemic Measures and Public Concerns from Twitter Arabic Data Using Distributed Machine Learning

“…Additionally, they analyzed the time and location for the geotagged tweets (in our work, we use multiple methods for the location extraction of tweets). Li et al [ 61 ] detected stress symptoms related to COVID-19 in the United States. They integrated a Correlation Explanation (CorEx) learning algorithm and clinical Patient Health Questionnaire (PHQ) lexicon and proposed a CorExQ9 algorithm.…”

Can social media data be used to evaluate the risk of human interactions during the COVID-19 pandemic?

“…Their results revealed that anti-vaccination users on Twitter became highly entangled with undecided users in the main online network, whereas pro-vaccination users are more peripheral in the network. Li et al [ 39 ] applied machine learning techniques to detect stress symptoms-related tweets on Twitter and manifested that people’s stress symptoms expressed on Twitter have a strong correlation with increasing cases. They also discovered that the main stressors switched from concerns on the increase of reported deaths to financial burdens and economic downturns.…”