The Emotional Impact of COVID-19 News Reporting: A Longitudinal Study Using Natural Language Processing

Abstract

The emotional impact of the COVID-19 pandemic and ensuing social restrictions has been profound, with widespread negative effects on mental health. We made use of the natural language processing and large-scale Twitter data to explore this in depth, identifying emotions in COVID-19 news content and user reactions to it, and how these evolved over the course of the pandemic. We focused on major UK news channels, constructing a dataset of COVID-related news tweets (tweets from news organisations) and user comments made in response to these, covering Jan 2020 to April 2021. Natural language processing was used to analyse topics and levels of anger, joy, optimism, and sadness. Overall, sadness was the most prevalent emotion in the news tweets, but this was seen to decline over the timeframe under study. In contrast, amongst user tweets, anger was the overall most prevalent emotion. Time epochs were defined according to the time course of the UK social restrictions, and some interesting effects emerged regarding these. Further, correlation analysis revealed significant positive correlations between the emotions in the news tweets and the emotions expressed amongst the user tweets made in response, across all channels studied. Results provide unique insight onto how the dominant emotions present in UK news and user tweets evolved as the pandemic unfolded. Correspondence between news and user tweet emotional content highlights the potential emotional effect of online news on users and points to strategies to combat the negative mental health impact of the pandemic.

Beyond fear and anger: A global analysis of emotional response to Covid-19 news on Twitter

“…This suggests that news about governmental actions instigated a higher level of negative feelings in people. This is consistent with previous findings [5] , [50] . Investigating the reasons for such a negative emotional response from society may help policymakers develop more effective methods for crisis management that can be accepted and supported by a larger part of society.…”

“…The media’s framing of health messages plays a vital role in shaping the community’s perception of emerging public health issues [3] , [4] . However, Covid-19 news often contains distressing content, such as death tolls, which can contribute to negative emotions in the audience [5] , [6] , [7] . This can discourage people from following the news, potentially limiting the effectiveness of crisis mitigation measures [8] .…”

“…Natural language processing (NLP) techniques have been used to investigate the sentiments in the Covid-19 news headlines [11] , [12] , and emotions among user posts on social networks [13] , [14] . NLP studies have identified correlations between emotions in news tweets and user responses, and provided valuable insights into how these patterns evolved as the pandemic unfolded [5] . Qualitative research has also been conducted on this topic [15] .…”

Longitudinal analysis of behavioral factors and techniques used to identify vaccine hesitancy among Twitter users: Scoping review

“…For user demographics and profile data extraction, different techniques are reported in the included studies, such as articles 20 , 21 that used m3 inference in Python for geographical information extraction. Article 21 also used “Geopy and Pycountry” libraries, while 25 used DeepFace and 41 used a named entity recognizer (NER) for user demographics and geographical information extraction. Several geographical regions are covered for users’ psychological and behavioral analysis toward vaccination.…”

“… 19 , 30 , 32 , 33 , 35 , 37 , 38 , 40 , 42 The second highest reported region for longitudinal analysis is the UK and reported in ( N = 8 ~ 29%) research studies. 22 , 23 , 33 , 34 , 38 , 41 , 44 , 46 India and Pakistan reported in retrospective studies 22 , 34 , 38 for users’ behavior analysis toward vaccination. Australia and Brazil reported in ( N = 4 ~ 14%) studies 21 , 22 , 34 , 38 for attitude analysis toward vaccination longitudinally.…”