Social Noise and the Impact of Misinformation on COVID-19 Preventive Measures: Comparative Data Analysis Using Twitter Masking Hashtags

Abstract

The widespread transmission of misinformation regarding the COVID-19 pandemic on social media has become a severe concern for various reasons such as containing the spread of the virus, taking preventive measures, and so on. According to the recent studies, misinformation and conspiracy theories spread on social media have hampered efforts to limit the infection, which has been exacerbated in some instances by politicians and celebrities. Misunderstandings about COVID-19 and wearing a mask sparked much debate. As time went on, a sizable portion of the population continued to refuse to wear masks, owing to extrinsic considerations, such as politics, ideology, personal views, and health concerns. In this study, we look at the concerns surrounding three Twitter hashtags (#masks, #maskup, and #maskoff) in order to understand better how social noise can lead to unintended misinformation. Sentiment analysis, topic modelling, and contextual analysis were used to compare and contrast two datasets relevant to these hashtags, one gathered in 2020 and the other in 2021. According to sentiment analysis, people’s emotions differed between hashtags, and the majority of tweets were based on social media users’ personal opinions. Topic modelling results revealed the prevalence of social noise leading to the unintended spread of misinformation on Twitter. The content analysis results show that while the #maskoff hashtag is used to resist masking influenced by factors, such as misinformation, conspiracy theories, and ideology, the #masks and #maskup hashtags were generally positive and used more to raise awareness of the benefits of wearing masks.