Mapping emotions on social media during the COVID-19 Pandemic

Keywords: emotions, mental health, social media
Session Type: Virtual Paper Abstract
Day: Saturday
Session Start / End Time: 2/26/2022 09:40 AM (Eastern Time (US & Canada)) - 2/26/2022 11:00 AM (Eastern Time (US & Canada))
Room: Virtual 4

Abstract

Local or global events can affect people’s emotions collectively. For example, the COVID-19 pandemic lowered emotional well-being significantly. The emotional state often influences people’s health and contributes to productivity and other positive/negative outcomes. Therefore, the implications of decreased emotional well-being are related to mental health concerns such as stress, depression, and anxiety. A person’s use of language conveys their feeling and emotions directly and this can be used as the estimation of mental health conditions. Previous studies have shown that social media data can reflect a user’s health behaviors while also being useful for providing mental health information at a finer space and temporal resolution. Therefore, we use tweets collected from five American cities during the COVID-19 pandemic to illustrate the spatiotemporal distribution of tweets that contain negative emotions that could indicate potential mental disorders during the COVID-19 pandemic. Geolocated tweets were collected by using a set of mental health related keywords. The result of this research shows how people in each city present their emotions on social media from that period of time and it can inform decision makers and public health agencies to get prepared in response to surging mental health problems and take preventative strategies.