ABSTRACT
BACKGROUND: Social media platforms have emerged as a valuable data source for public health research and surveillance. Monitoring of social media and user-generated data on the web enables timely and inexpensive collection of information, overcoming time lag and cost of traditional health reporting systems. OBJECTIVES: To identify personally experienced COVID-19 vaccine reactions expressed on Twitter and validate the findings against an established vaccine reactions reporting system. METHODS: We collected around three million tweets from 1.4 million users between 1 February 2021 - 31 January 2022, using COVID-19 vaccines and vaccine reactions keyword lists. We performed topic modelling on a sample of the data and applied a modified F1 scoring technique to identify a topic that best differentiated vaccine-related personal health mentions. We then manually annotated 4,000 of the records from this topic, which were used to train a transformer-based classifier to identify likely personally experienced vaccine reactions. Applying the trained classifier to the entire dataset allowed us to select records we could use to quantify potential vaccine side effects. Adverse events following immunization (AEFI) referred to in these records were compared with those reported to the state of Victoria's spontaneous vaccine safety surveillance system, SAEFVIC. RESULTS: The most frequently mentioned potential vaccine reactions generally aligned with SAEFVIC data. Notable exceptions were increased Twitter reporting of bleeding-related AEFI and allergic reactions, and more frequent SAEFVIC reporting of cardiac AEFI. CONCLUSIONS: Social media conversation can be used as a supplementary data source for detecting vaccine adverse event mentions. More work is required to verify the data.
ABSTRACT
Surveillance of Adverse Events Following Vaccination in the Community (SAEFVIC), Victoria's vaccine safety service for reporting adverse events following immunisation (AEFI), has provided integrated spontaneous surveillance and clinical services for individuals affected by AEFI since 2007. We describe SAEFVIC's response to the COVID-19 vaccine program, and reflect on lessons learned for vaccine safety. The massive scale of the Australian COVID-19 vaccine program required rapid adaptations across all aspects of SAEFVIC's vaccine safety services. Collection of AEFI reports was streamlined and expanded, incorporating both spontaneous and active surveillance data. Dramatically increased report volumes were managed with additional staffing, and innovations to automate, filter, and triage reports for priority follow up. There were two major adverse events of special interest (AESI): thrombosis with thrombocytopaenia syndrome and myocarditis, with multiple other AESI also investigated. Rapid escalation mechanisms to respond to AESI were established, along with AESI-specific databases for enhanced monitoring. Vaccine education and training resources were developed and public-facing vaccine safety reports updated weekly. Frequent communication with local and national government and regulatory bodies, and consultation with specialist groups was essential. The COVID-19 vaccine program has highlighted the importance of vaccine safety in supporting public confidence in vaccines and informing evidence-based immunisation policy. Supporting the COVID-19 vaccine program has required flexibility in adapting to policy changes and evolving vaccine safety signals, careful triage and prioritisation, informatics innovation, and enhanced engagement with the public regarding vaccine safety. Long-term investment to continue strengthening vaccine safety systems, building on lessons learned, will be essential for the ongoing success of Australian vaccination programs.