Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Japanese AI Agent System on Human Papillomavirus Vaccination: System Design

Junyu Liu, Siwen Yang, Dexiu Ma, Qian Niu, Zequn Zhang, Momoko Nagai-Tanima, Tomoki Aoyama

TL;DR

This work tackles HPV vaccine hesitancy in Japan by designing a dual-purpose AI system that combines a Retrieval-Augmented Generation chatbot with a multi-source analytics pipeline. The architecture centers a vector database and a ReAct-based controller that iteratively retrieves information from papers, official documents, news, and social media to answer public queries with verified sources while generating institutional reports. The evaluation demonstrates high-quality performance across single-turn and multi-turn chatbot interactions and robust report generation with strong source attribution and temporal analysis. The approach offers a transferable framework for scalable, multilingual public health communication and discourse monitoring applicable to other vaccines and medical domains.

Abstract

Human papillomavirus (HPV) vaccine hesitancy poses significant public health challenges, particularly in Japan where proactive vaccination recommendations were suspended from 2013 to 2021. The resulting information gap is exacerbated by misinformation on social media, and traditional ways cannot simultaneously address individual queries while monitoring population-level discourse. This study aimed to develop a dual-purpose AI agent system that provides verified HPV vaccine information through a conversational interface while generating analytical reports for medical institutions based on user interactions and social media. We implemented a system comprising: a vector database integrating academic papers, government sources, news media, and social media; a Retrieval-Augmented Generation chatbot using ReAct agent architecture with multi-tool orchestration across five knowledge sources; and an automated report generation system with modules for news analysis, research synthesis, social media sentiment analysis, and user interaction pattern identification. Performance was assessed using a 0-5 scoring scale. For single-turn evaluation, the chatbot achieved mean scores of 4.83 for relevance, 4.89 for routing, 4.50 for reference quality, 4.90 for correctness, and 4.88 for professional identity (overall 4.80). Multi-turn evaluation yielded higher scores: context retention 4.94, topic coherence 5.00, and overall 4.98. The report generation system achieved completeness 4.00-5.00, correctness 4.00-5.00, and helpfulness 3.67-5.00, with reference validity 5.00 across all periods. This study demonstrates the feasibility of an integrated AI agent system for bidirectional HPV vaccine communication. The architecture enables verified information delivery with source attribution while providing systematic public discourse analysis, with a transferable framework for adaptation to other medical contexts.

Japanese AI Agent System on Human Papillomavirus Vaccination: System Design

TL;DR

This work tackles HPV vaccine hesitancy in Japan by designing a dual-purpose AI system that combines a Retrieval-Augmented Generation chatbot with a multi-source analytics pipeline. The architecture centers a vector database and a ReAct-based controller that iteratively retrieves information from papers, official documents, news, and social media to answer public queries with verified sources while generating institutional reports. The evaluation demonstrates high-quality performance across single-turn and multi-turn chatbot interactions and robust report generation with strong source attribution and temporal analysis. The approach offers a transferable framework for scalable, multilingual public health communication and discourse monitoring applicable to other vaccines and medical domains.

Abstract

Human papillomavirus (HPV) vaccine hesitancy poses significant public health challenges, particularly in Japan where proactive vaccination recommendations were suspended from 2013 to 2021. The resulting information gap is exacerbated by misinformation on social media, and traditional ways cannot simultaneously address individual queries while monitoring population-level discourse. This study aimed to develop a dual-purpose AI agent system that provides verified HPV vaccine information through a conversational interface while generating analytical reports for medical institutions based on user interactions and social media. We implemented a system comprising: a vector database integrating academic papers, government sources, news media, and social media; a Retrieval-Augmented Generation chatbot using ReAct agent architecture with multi-tool orchestration across five knowledge sources; and an automated report generation system with modules for news analysis, research synthesis, social media sentiment analysis, and user interaction pattern identification. Performance was assessed using a 0-5 scoring scale. For single-turn evaluation, the chatbot achieved mean scores of 4.83 for relevance, 4.89 for routing, 4.50 for reference quality, 4.90 for correctness, and 4.88 for professional identity (overall 4.80). Multi-turn evaluation yielded higher scores: context retention 4.94, topic coherence 5.00, and overall 4.98. The report generation system achieved completeness 4.00-5.00, correctness 4.00-5.00, and helpfulness 3.67-5.00, with reference validity 5.00 across all periods. This study demonstrates the feasibility of an integrated AI agent system for bidirectional HPV vaccine communication. The architecture enables verified information delivery with source attribution while providing systematic public discourse analysis, with a transferable framework for adaptation to other medical contexts.
Paper Structure (27 sections, 4 figures, 6 tables)

This paper contains 27 sections, 4 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. System Architecture
  4. Data Collection and Database
  5. Chatbot Implementation
  6. Architecture
  7. Operational Workflow
  8. Report Generation System
  9. System Architecture
  10. Social Media Analysis
  11. PDF Report Assembly
  12. Evaluation Framework
  13. Chatbot Evaluation Methodology
  14. Report Generation Evaluation Methodology
  15. Results
  16. ...and 12 more sections

Figures (4)

  • Figure 1: Overall system architecture showing the integration of data collection, vector database, chatbot interface, and report generation components.
  • Figure 2: Chatbot operational workflow showing the iterative ReAct agent architecture. The user query flows through reasoning and tool selection, with the controller dynamically selecting from five specialized tools (papers, web, social media, news, chitchat). Results are observed and validated through a citation validation mechanism before generating the final response with proper source attribution.
  • Figure 3: Report generation system architecture. Data flows from external news sources and vector database collections (papers, social media, user conversations) through specialized analysis modules. The social media analyzer performs topic modeling, stance detection, and misinformation detection. All analysis results are integrated through cross-source aggregation before final report generation.
  • Figure 4: Example chatbot response demonstrating professional medical tone, structured information delivery, evidence-based recommendations with citations, and personalized guidance.