Use of large language models as a scalable approach to understanding public health discourse

Online public health discourse is becoming more and more important in shaping public health dynamics. Large Language Models (LLMs) offer a scalable solution for analysing the vast amounts of unstructured text found on online platforms. Here, we explore the effectiveness of Large Language Models (LLMs), including GPT models and open-source alternatives, for extracting public stances towards vaccination from social media posts. Using an expert-annotated dataset of social media posts related to vaccination, we applied various LLMs and a rule-based sentiment analysis tool to classify the stance towards vaccination. We assessed the accuracy of these methods through comparisons with expert annotations and annotations obtained through crowdsourcing. Our results demonstrate that few-shot prompting of best-in-class LLMs are the best performing methods, and that all alternatives have significant risks of substantial misclassification. The study highlights the potential of LLMs as a scalable tool for public health professionals to quickly gauge public opinion on health policies and interventions, offering an efficient alternative to traditional data analysis methods. With the continuous advancement in LLM development, the integration of these models into public health surveillance systems could substantially improve our ability to monitor and respond to changing public health attitudes. Authors summary We examined how Large Language Models (LLMs), including GPT models and open-source versions, can analyse online discussions about vaccination from social media. Using a dataset with expert-checked posts, we tested various LLMs and a sentiment analysis tool to identify public stance towards vaccination. Our findings suggest that using LLMs, and prompting them with labelled examples, is the most effective approach. The results show that LLMs are a valuable resource for public health experts to quickly understand the dynamics of public attitudes towards health policies and interventions, providing a faster and efficient option compared to traditional methods. As LLMs continue to improve, incorporating these models into digital public health monitoring could greatly improve how we observe and react to dynamics in public health discussions. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This work was supported by Fondation Botnar and the European Union's Horizon H2020 grant VEO (874735). ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The study used only openly available data from X (former Twitter) I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes The data (list of tweets identifiers and summarised anonymised datasets) and R and Python code used can be found in the online repository at [https://github.com/digitalepidemiologylab/llm\_crowd\_experts_annotation][1]. [https://github.com/digitalepidemiologylab/llm\_crowd\_experts_annotation][1] [1]: https://github.com/digitalepidemiologylab/llm_crowd_experts_annotation