Examining the Utility of Social Media in COVID-19 Vaccination: Unsupervised Learning of 672,133 Twitter Posts

"Given the severity of the COVID-19 pandemic and the time pressure to accelerate COVID-19 vaccination, there is an urgent need to gain insight into the psychological proposition of how people think and feel - specific to the newly developed COVID-19 vaccines - so that effective recommendations or strategies may be proposed to improve vaccine uptake..."

There is a risk that global mass COVID-19 vaccination efforts may be hampered by widespread vaccine hesitancy. Traditionally, research on attitude, perception, and behaviour has often relied on methodologies such as surveys, interviews, or focus group discussions. However, the field of infodemiology recognises the utility of real-time information across the internet in informing public health and public policy. This study examines public Twitter conversations about COVID-19 vaccines with the intention to understand which issues have captured public attention and to identify strategies for addressing COVID-19 vaccine hesitancy and improving vaccine uptake.

Twitter was searched for tweets related to COVID-19 and vaccines over an 11-week period after November 18 2020, following a press release regarding the first effective vaccine. An unsupervised machine learning approach (i.e., structural topic modeling) was used to identify topics from tweets, with each topic further grouped into themes using manually conducted thematic analysis. The guiding theoretical framework is the COM-B model:

• Capability: an individual's psychological and physical capacity to make the behaviour possible, such as having the necessary knowledge and skills to perform it.
• Opportunity: attributes that lie outside the individual physically or socially that make the behaviour possible, such as environmental factors or social and cultural norms.
• Motivation: the automatic or reflective mental processes that energise and direct behaviour, which can include the conscious thought process in deciding on a behaviour or a less conscious thought process driven by desires or habits.

Sentiment analysis of the tweets was also performed using the open-source, rule-based machine learning model VADER (Valence Aware Dictionary and Sentiment Reasoner), which is based on a human-curated lexicon of 7,500 emotion-related words and 5 human-interpretable rules that identify sentiment intensity.

Analysing the tweets related to COVID-19 vaccines posted by individuals around the world during the study period (N=672,133), the researchers identified 59 topics, with 6 overarching themes:

1. Emotional reactions related to COVID-19 vaccines (19.3%) - e.g., feeling hopeful after receiving the vaccination;
2. Public concerns related to COVID-19 vaccines (19.6%) - e.g., concerns about misinformation related to COVID-19 vaccines;
3. Discussions about news items related to COVID-19 vaccines (13.3%) - e.g., news about the launch of the COVID-19 vaccination drive in India;
4. Public health communications about COVID-19 vaccines (10.3%) - e.g., using radio as a medium to clarify questions related to COVID-19 vaccines;
5. Discussions about approaches to COVID-19 vaccination drives (17.1%) - e.g., involving public figures to gain public trust regarding COVID-19 vaccines; and
6. Discussions about the distribution of COVID-19 vaccines (20.3%) - e.g., call for equitable access to COVID-19 vaccines across different countries.

Tweets with negative sentiments largely fell within the themes of emotional reactions and public concerns related to COVID-19 vaccines.

The researchers examined the barriers and facilitators related to COVID-19 vaccination by matching the 59 topics to the 3 components in the COM-B model. In brief, barriers to COVID-19 vaccination could be grouped into those related to capability (e.g., vaccine misinformation), opportunity (e.g., limited access to the vaccines and poorly planned vaccination drives), and motivation (e.g., public concerns related to the vaccines). Similarly, facilitators of COVID-19 vaccination could be grouped into those related to capability (e.g., access to accurate information related to the vaccines and the right approach to delivering public education), opportunity (e.g., sufficient access to the vaccines and well-planned vaccination drives), and motivation (e.g., public perception about the threat of COVID-19 and public optimism about the vaccines).

In general, tweets related to facilitators had a higher prevalence than those related to barriers. Facilitators related to capability were highly talked about in the initial weeks after the press release, followed by a declining trend in the subsequent weeks. Facilitators related to opportunity rose sharply over the 11 weeks, while facilitators related to motivation peaked around the sixth week. In contrast, tweets related to barriers remained largely constant throughout the study period, with those related to motivation being more prevalent than those related to capability or opportunity.

The researchers suggest that the findings on the 6 themes may potentially have policy implications for improving COVID-19 vaccine uptake. They provide an expanded model (see Figure 4 in the paper) that may provide contextual details on the key processes that are relevant to successful COVID-19 vaccination drives. For example, in the planning of COVID-19 vaccination, Figure 4 highlights the need for policymakers to be mindful of common emotions and concerns in the community, which may then be addressed through targeted public health communications and through debunking of misinformation. Figure 4 also elaborates on practical issues that need to be addressed in vaccination drives, such as engagement of stakeholders, clarification of priority groups for vaccination, and equitable access to the vaccines.

The findings on the barriers and facilitators to COVID-19 vaccination (see Table 2 and Figure 3) present a different set of information to policymakers. For example, Figure 3 highlights a worrisome trend: Barriers related to individuals' motivations to receive COVID-19 vaccines have remained prominent and unchanging across time and may be an area that requires further intervention. Given that the barriers related to motivation were largely driven by public concerns regarding COVID-19 vaccines, such as those related to vaccine safety as seen in Table 2, policymakers may potentially adopt some of the proposed interventions related to the COM-B model to address these prevailing public concerns. For example, policymakers could modify barriers related to motivation in the COM-B model by communicating to the public the safety and effectiveness of COVID-19 vaccines (i.e., persuasion), broadcasting special events with public figures or celebrities receiving the vaccines (i.e., modeling), and/or lifting COVID-19 restrictions related to social gatherings among those who have received the vaccines (i.e., incentivisation).

Findings from this study also demonstrate the potential roles of social media in ongoing COVID-19 vaccination drives. Figure 5 in the paper illustrates these roles: surveillance and monitoring of public concerns regarding COVID-19 vaccines; a platform for accurate communication of vaccine-related information; and evaluation of government responses in the vaccine rollout.

In conclusion: "The findings from this study may facilitate the formulation of comprehensive strategies to improve COVID-19 vaccine uptake; they highlight the key processes that require attention in the planning of COVID-19 vaccination and provide feedback on evolving barriers and facilitators in ongoing vaccination drives to allow for further policy tweaks."