Surveilling COVID-19 Emotional Contagion on Twitter by Sentiment Analysis

Abstract

BackgroundThe fight against the COVID-19 pandemic seems to encompass a social media debate, possibly resulting in emotional contagion and the need for novel surveillance approaches. In the current study, we aimed to examine the flow and content of tweets, exploring the role of COVID-19 key events on the popular Twitter platform.MethodsUsing representative freely available data, we performed a focused, social media-based analysis to capture COVID-19 discussions on Twitter, considering sentiment and longitudinal trends between January 19 and March 3, 2020. Different populations of users were considered. Core discussions were explored measuring tweets’ sentiment, by both computing a polarity compound score with 95% Confidence Interval and using a transformer-based model, pretrained on a large corpus of COVID-19-related Tweets. Context-dependent meaning and emotion-specific features were considered.ResultsWe gathered 3,308,476 tweets written in English. Since the first World Health Organization report (January 21), negative sentiment proportion of tweets gradually increased as expected, with amplifications following key events. Sentiment scores were increasingly negative among most active users. Tweets content and flow revealed an ongoing scenario in which the global emergency seems difficult to be emotionally managed, as shown by sentiment trajectories.ConclusionsIntegrating social media like Twitter as essential surveillance tools in the management of the pandemic and its waves might actually represent a novel preventive approach to hinder emotional contagion, disseminating reliable information and nurturing trust. There is the need to monitor and sustain healthy behaviors as well as community supports also via social media-based preventive interventions.

Changes in Public Response Associated With Various COVID-19 Restrictions in Ontario, Canada: Observational Infoveillance Study Using Social Media Time Series Data

“…Scores of -0.05 and under were negative, scores of +0.05 and above were positive, and scores in between were neutral. These thresholds are conventional for studies using VADER [19,20], and classification by human raters was found to be well-matched to VADER results when using these scoring thresholds [21].…”

What Is the Role of Resilience and Coping Strategies on the Mental Health of the General Population during the COVID-19 Pandemic? Results from the Italian Multicentric COMET Study

“…An interesting finding is related to the use of searching for information as an adaptive coping strategy, which appears to be a negative predictor of resilience. This finding highlights the negative role held by media during the pandemic, with sensationalistic (and sometimes biased) news rapidly spread through social media, and the tendency of the general population to look for information more frequently than in the past [ 83 ]. For this tendency, the WHO has coined the term “infodemic”, suggesting its maladaptive role as a coping strategy [ 84 , 85 ].…”

Understanding the emotional response to COVID‐19 information in news and social media: A mental health perspective

“…Regarding mental health implications, some work is emerging using these tools to study the psychological impact of the pandemic on Twitter users (Crocamo et al, 2021 ; Valdez et al, 2020 ) and users of other social media platforms. Using sentiment and thematic analysis, these studies provided insights into how users' emotional responses and topics of interest evolved as the pandemic unfolded.…”