Negative perceptions of COVID-19 have decreased intensively on Twitter after the start of the vaccination campaign

An in-depth analysis of more than 120 million Twitter posts around the world has shown that user perceptions of the Covid-19 pandemic have become less negative as it has progressed. In an article published in Frontiers, its authors found a significant decrease in negativity in countries that have rolled out extensive vaccination programs, such as the United States, United Kingdom and Canada.

The devastation and distress caused by the Covid-19 pandemic to millions of lives is no doubt, but trying to assess an entire planet’s changing perception of disease over time can seem like an almost impossible task.

Yet with some estimates showing that nearly 4.5 billion people now use some form of online social media, researchers are tapping into this vast resource in an attempt to create a clearer picture of how the perception of this event is. life changing has changed since the start of 2020.

Now, by posting their findings in Frontiers in Psychology, scientists from Vanderbilt University in the United States and the Federal Technological University of Paraná in Brazil tapped a huge dataset of Twitter posts (tweets) to show that the number of negative posts on Covid-19 is on the rise. decline, especially in countries that have rolled out extensive immunization programs.

The “Covid-19 Twitter Conversations Dataset” – available free online to researchers and containing more than a billion tweets posted during the pandemic – was the basis of this research. For the sake of precision in detecting negative feelings, the researchers focused on 120 million messages in English between March 1, 2020 and June 2021.

► Read the original article
► Download the original article (pdf)

Trump’s power

Dozens of negative words were analyzed by the team – including “anxiety”, “idiot”, “rage” and “horrible” – with a peculiarity of this database being that it contains only original tweets, which means that it rejects retweets (a repost of an original tweet) that could skew their results.

Instead of relying on previously tested sentiment algorithms, the researchers followed the traditional procedure of counting the number of negative words.

The process of counting the number of negative words in a message, they wrote, is much less computationally intensive than calculating a sentiment score through machine learning algorithms giving their approach a “clear advantage.”

“We have shown that negative perception skyrocketed in April 2020 and has declined steadily since then,” said Alexander Maier, associate professor of ophthalmology and visual sciences at Vanderbilt University.

“Over time over the past year, we have seen fewer and fewer negative emotional words being used in tweets mentioning the pandemic.”

There have also been some interesting findings in the data, such as the influence of former US President Donald Trump on Twitter’s conversation around Covid-19.

“We observe that the negative perception in the tweets shows peaks from October 2 to October 6, 2020, likely related to news released on October 2 that [Trump] tested positive for Covid-19. After this event, the negative perception in tweets began to drop steadily. “

Surprising paradox

Additionally, more unexpected ones emerged while viewing the tweets in the United States. While it could be assumed that an increase in Covid-19 deaths would lead to an increase in negative perception, the opposite has been the case.

“What the data reveals is that the increase in Covid-19 deaths in the United States, after November 2020, coincides with a pronounced decrease in negative perception – a paradox,” the authors wrote.

“Strangely enough, a similar paradox arose when the pandemic began in the United States: The psychological distress index rapidly declined just after a few weeks as the number of deaths continued to rise. “

Trying to understand this paradox, they analyzed vaccination statistics for the United States, United Kingdom and Canada; revealing a strong relationship between the decline in negative perception of the pandemic on Twitter and the increase in vaccination in these countries.

A previous study of sentiment on Twitter found that out of 4 million tweets written in English, most came from the United States (42.5%), India (10.8%), Canada (5, 9%) and the United Kingdom (5.9%).

Impact of vaccinations

“The take-home message from this article is: People’s negativity has gone down,” they wrote.

“In particular, people’s negativity decreased in an almost linear fashion as vaccination increased exponentially, suggesting a slow emotional adaptation to a rapidly changing situation. For this reason, it seems reasonable to argue that the vaccination campaign played a crucial role in decreasing people’s negativity.

However, the rise of science denial on platforms such as Twitter towards Covid-19 vaccines and the spread of so-called “fake news” is potentially skewing the data.

So, is it possible that the negative perception falling on Twitter is related to the company taking action against disinformation or disinformation of Covid-19?

“We don’t have a definitive answer to this question,” Maier said. “That being said, we found a long term trend of negative perception that has steadily declined, monitoring massive amounts of tweets and users. This decrease in negative perception seems more suggestive of a natural process, reflecting a genuine mood change in the English-speaking population.

With this new knowledge, Maier and the team plan to apply similar analyzes to investigate the emotional foundations of reluctance to vaccinate Covid-19.

Comments are closed.