School of Nursing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong.
Discipline of Information Technology, Media and Communications, Murdoch University, Perth, Australia.
J Med Internet Res. 2021 May 19;23(5):e26953. doi: 10.2196/26953.
COVID-19 is one of the greatest threats to human beings in terms of health care, economy, and society in recent history. Up to this moment, there have been no signs of remission, and there is no proven effective cure. Vaccination is the primary biomedical preventive measure against the novel coronavirus. However, public bias or sentiments, as reflected on social media, may have a significant impact on the progression toward achieving herd immunity.
This study aimed to use machine learning methods to extract topics and sentiments relating to COVID-19 vaccination on Twitter.
We collected 31,100 English tweets containing COVID-19 vaccine-related keywords between January and October 2020 from Australian Twitter users. Specifically, we analyzed tweets by visualizing high-frequency word clouds and correlations between word tokens. We built a latent Dirichlet allocation (LDA) topic model to identify commonly discussed topics in a large sample of tweets. We also performed sentiment analysis to understand the overall sentiments and emotions related to COVID-19 vaccination in Australia.
Our analysis identified 3 LDA topics: (1) attitudes toward COVID-19 and its vaccination, (2) advocating infection control measures against COVID-19, and (3) misconceptions and complaints about COVID-19 control. Nearly two-thirds of the sentiments of all tweets expressed a positive public opinion about the COVID-19 vaccine; around one-third were negative. Among the 8 basic emotions, trust and anticipation were the two prominent positive emotions observed in the tweets, while fear was the top negative emotion.
Our findings indicate that some Twitter users in Australia supported infection control measures against COVID-19 and refuted misinformation. However, those who underestimated the risks and severity of COVID-19 may have rationalized their position on COVID-19 vaccination with conspiracy theories. We also noticed that the level of positive sentiment among the public may not be sufficient to increase vaccination coverage to a level high enough to achieve vaccination-induced herd immunity. Governments should explore public opinion and sentiments toward COVID-19 and COVID-19 vaccination, and implement an effective vaccination promotion scheme in addition to supporting the development and clinical administration of COVID-19 vaccines.
就医疗保健、经济和社会而言，COVID-19 是近代历史上对人类的最大威胁之一。到目前为止，它没有任何缓解的迹象，也没有被证实有效的治疗方法。疫苗接种是预防新型冠状病毒的主要生物医学措施。然而，社交媒体上反映的公众偏见或情绪，可能会对实现群体免疫的进程产生重大影响。
本研究旨在使用机器学习方法从 Twitter 上提取与 COVID-19 疫苗接种相关的主题和情绪。
我们从澳大利亚的 Twitter 用户那里收集了 2020 年 1 月至 10 月期间包含 COVID-19 疫苗相关关键词的 31100 条英文推文。具体来说，我们通过可视化高频词云以及词项之间的相关性来分析推文。我们构建了一个潜在狄利克雷分配（LDA）主题模型，以识别在大量推文中常见的讨论主题。我们还进行了情感分析，以了解澳大利亚与 COVID-19 疫苗接种相关的总体情绪和情感。
我们的分析确定了 3 个 LDA 主题：（1）对 COVID-19 及其疫苗接种的态度；（2）倡导针对 COVID-19 的感染控制措施；（3）对 COVID-19 控制的误解和抱怨。几乎三分之二的所有推文的情绪表达了对 COVID-19 疫苗的正面公众意见；三分之一左右为负面。在 8 种基本情绪中，信任和期待是推文中观察到的两种突出的积极情绪，而恐惧是最主要的消极情绪。
我们的研究结果表明，澳大利亚的一些 Twitter 用户支持针对 COVID-19 的感染控制措施，并驳斥了错误信息。然而，那些低估 COVID-19 风险和严重程度的人可能会用阴谋论来合理化他们对 COVID-19 疫苗接种的立场。我们还注意到，公众的积极情绪水平可能不足以提高疫苗接种率，使其达到足以实现疫苗接种诱导的群体免疫的水平。政府应该探索公众对 COVID-19 和 COVID-19 疫苗接种的意见和情绪，并在支持 COVID-19 疫苗的开发和临床管理的同时，实施有效的疫苗接种推广计划。
