Bridging the Gap: Leveraging Retrieval-Augmented Generation to Better Understand Public Concerns about Vaccines

• URL: http://arxiv.org/abs/2507.12840v1
• Date: Thu, 17 Jul 2025 06:59:52 GMT
• Title: Bridging the Gap: Leveraging Retrieval-Augmented Generation to Better Understand Public Concerns about Vaccines
• Authors: Muhammad Javed, Sedigh Khademi Habibabadi, Christopher Palmer, Hazel Clothier, Jim Buttery, Gerardo Luis Dimaguila,
• Abstract summary: Vaccine hesitancy threatens public health, leading to delayed or rejected vaccines.<n>Social media is a vital source for understanding public concerns, and traditional methods like topic modelling often struggle to capture nuanced opinions.<n>To address these limitations, we developed a tool (VaxPulse Query Corner) using the Retrieval Augmented Generation technique.<n>It addresses complex queries about public vaccine concerns on various online platforms, aiding public health administrators and stakeholders in understanding public concerns and implementing targeted interventions to boost vaccine confidence.
• Score: 0.5277756703318045
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Vaccine hesitancy threatens public health, leading to delayed or rejected vaccines. Social media is a vital source for understanding public concerns, and traditional methods like topic modelling often struggle to capture nuanced opinions. Though trained for query answering, large Language Models (LLMs) often miss current events and community concerns. Additionally, hallucinations in LLMs can compromise public health communication. To address these limitations, we developed a tool (VaxPulse Query Corner) using the Retrieval Augmented Generation technique. It addresses complex queries about public vaccine concerns on various online platforms, aiding public health administrators and stakeholders in understanding public concerns and implementing targeted interventions to boost vaccine confidence. Analysing 35,103 Shingrix social media posts, it achieved answer faithfulness (0.96) and relevance (0.94).

Related papers

• VaxPulse: Monitoring of Online Public Concerns to Enhance Post-licensure Vaccine Surveillance [0.3958317527488535]
  We describe how we enhanced the reporting surveillance system of Victoria's vaccine safety service, SAEFVIC.<n>Using VaxPulse, a multi-step framework, we integrate adverse events following immunisation with sentiment analysis.<n>We emphasise the need to address non-English languages to stratify concerns across ethno-lingual communities.
  arXiv  Detail & Related papers  (2025-07-07T04:18:08Z)
• Modeling the amplification of epidemic spread by individuals exposed to misinformation on social media [41.31724592098777]
  We employ an epidemic model that incorporates a large, mobility-informed physical contact network and social media data.<n>We simulate various scenarios to understand how epidemic spreading can be affected by misinformation spreading through one particular social media platform.<n>We estimate the additional portion of the U.S. population that would become infected over the course of the COVID-19 epidemic in the worst-case scenario.
  arXiv  Detail & Related papers  (2024-02-17T18:01:43Z)
• Visualizing Relation Between (De)Motivating Topics and Public Stance toward COVID-19 Vaccine [0.0]
  In this study, we proposed an interactive visualization tool to inspect and analyze the topics that resonated among Twitter-sphere during the COVID-19 pandemic. This tool can easily be generalized for any scenario for visual analysis and to increase the transparency of social media data for researchers and the general population alike.
  arXiv  Detail & Related papers  (2023-06-21T09:01:53Z)
• Doctors vs. Nurses: Understanding the Great Divide in Vaccine Hesitancy among Healthcare Workers [64.1526243118151]
  We find that doctors are overall more positive toward the COVID-19 vaccines. Doctors are more concerned with the effectiveness of the vaccines over newer variants. Nurses pay more attention to the potential side effects on children.
  arXiv  Detail & Related papers  (2022-09-11T14:22:16Z)
• "Double vaccinated, 5G boosted!": Learning Attitudes towards COVID-19 Vaccination from Social Media [4.178929174617172]
  We leverage the textual posts on social media to extract and track users' vaccination stances in near real time. We integrate the recent posts of a user's social network neighbours to help detect the user's genuine attitude. Based on our annotated dataset from Twitter, the models instantiated from our framework can increase the performance of attitude extraction by up to 23%.
  arXiv  Detail & Related papers  (2022-06-27T17:04:56Z)
• "COVID-19 was a FIFA conspiracy #curropt": An Investigation into the Viral Spread of COVID-19 Misinformation [60.268682953952506]
  We estimate the extent to which misinformation has influenced the course of the COVID-19 pandemic using natural language processing models. We provide a strategy to combat social media posts that are likely to cause widespread harm.
  arXiv  Detail & Related papers  (2022-06-12T19:41:01Z)
• Echoes through Time: Evolution of the Italian COVID-19 Vaccination Debate [3.9758527669515518]
  We use a Twitter dataset spanning September 2019 - November 2021 to examine the state of polarization around vaccination. We find the stark division between supporters and hesitant individuals to continue throughout the vaccination campaign. However, we find an increasing commonality in the topical focus of the vaccine supporters and vaccine hesitant, pointing to a possible common set of facts the two sides may agree on.
  arXiv  Detail & Related papers  (2022-04-27T13:50:19Z)
• Classifying vaccine sentiment tweets by modelling domain-specific representation and commonsense knowledge into context-aware attentive GRU [9.8215089151757]
  Vaccine hesitancy and refusal can create clusters of low vaccine coverage and reduce the effectiveness of vaccination programs. Social media provides an opportunity to estimate emerging risks to vaccine acceptance by including geographical location and detailing vaccine-related concerns. Methods for classifying social media posts, such as vaccine-related tweets, use language models (LMs) trained on general domain text. We present a novel end-to-end framework consisting of interconnected components that use domain-specific LM trained on vaccine-related tweets and models commonsense knowledge into a bidirectional gated recurrent network (CK-BiGRU) with context-aware attention.
  arXiv  Detail & Related papers  (2021-06-17T15:16:08Z)
• Dark Web Marketplaces and COVID-19: before the vaccine [53.447910186085586]
  We analyse 851,199 listings extracted from 30 dark web marketplaces between January 1, 2020 and November 16, 2020. We identify 788 listings directly related to COVID-19 products and monitor the temporal evolution of product categories. We reveal how the online shadow economy has evolved during the COVID-19 pandemic and highlight the importance of a continuous monitoring of DWMs.
  arXiv  Detail & Related papers  (2020-08-04T14:27:41Z)
• Digital Ariadne: Citizen Empowerment for Epidemic Control [55.41644538483948]
  The COVID-19 crisis represents the most dangerous threat to public health since the H1N1 pandemic of 1918. Technology-assisted location and contact tracing, if broadly adopted, may help limit the spread of infectious diseases. We present a tool, called 'diAry' or 'digital Ariadne', based on voluntary location and Bluetooth tracking on personal devices.
  arXiv  Detail & Related papers  (2020-04-16T15:53:42Z)
• Falling into the Echo Chamber: the Italian Vaccination Debate on Twitter [65.7192861893042]
  We examine the extent to which the vaccination debate on Twitter is conductive to potential outreach to the vaccination hesitant. We discover that the vaccination skeptics, as well as the advocates, reside in their own distinct "echo chambers" At the center of these echo chambers we find the ardent supporters, for which we build highly accurate network- and content-based classifiers.
  arXiv  Detail & Related papers  (2020-03-26T13:55:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.