Tracking Emotional Changes in Texts Across Waves of the COVID-19 Pandemic

In this research paper, the authors investigate the emotional response of populations to the COVID-19 pandemic using text analysis methods. They utilize the Linguistic Inquiry and Word Count (LIWC) and the Syntax Aware LexicaL Emotion Engine (SALLEE) to score text samples based on self-reported emotions of participants. Experimental and naturalistic text samples are analyzed, and moderate correlations between self-reported emotions and software metrics are found. The topic of vaccination generally elicits positive sentiment, while the topic of government elicits negative sentiment. The authors highlight the importance of studying language with text analysis tools to gain insights into how communities and individuals react to traumatic events.

Read the research:

Words Left Behind - Tracking Emotional Changes in Experimental and Naturalistic Texts Acro

.

Download • 729KB