Exploring Community-Powered Conversational Agent for Health Knowledge Acquisition: A Case Study in Colorectal Cancer

2025-12-10

AI Summary

Young users in online health communities face challenges including content fragmentation, low information quality, and difficulty understanding medical terminology—particularly regarding colorectal cancer (CRC). To address these issues, we propose CanAnswer, a community-driven conversational agent designed for CRC knowledge acquisition. CanAnswer is the first system to systematically integrate heterogeneous real-world content from online health communities, grounded in user needs analysis, clinical expert validation, and cognitive load assessment. Its architecture combines retrieval-augmented generation (RAG), a lightweight knowledge graph, and user behavior modeling. In a controlled lab study (N=24), CanAnswer significantly improved users’ knowledge recall by 37.2% (p<0.01) and reduced cognitive load—evidenced by a 28.6% decrease in NASA-TLX scores (p<0.05). Six clinical experts unanimously endorsed its knowledge accuracy and decision-support potential. This work establishes a reproducible methodology and technical paradigm for delivering trustworthy, low-barrier community-based health knowledge services.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Question Answering

Application Category

• Web Mining and Content Analysis: Community question answering
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Online communities have become key platforms where young adults, actively seek and share information, including health knowledge. However, these users often face challenges when browsing these communities, such as fragmented content, varying information quality and unfamiliar terminology. Based on a survey with 56 participants and follow-up interviews, we identify common challenges and expected features for learning health knowledge. In this paper, we develop a computational workflow that integrates community content into a conversational agent named CanAnswer to facilitate health knowledge acquisition. Using colorectal cancer as a case study, we evaluate CanAnswer through a lab study with 24 participants and interviews with six medical experts. Results show that CanAnswer improves the recalled gained knowledge and reduces the task workload of the learning session. Our expert interviews (N=6) further confirm the reliability and usefulness of CanAnswer. We discuss the generality of CanAnswer and provide design considerations for enhancing the usefulness and credibility of community-powered learning tools.

Problem

• Develops a conversational agent for health knowledge acquisition
• Addresses fragmented content and quality issues in online communities
• Evaluates effectiveness in improving recall and reducing workload

Innovation

• Integrates community content into a conversational agent
• Uses computational workflow to facilitate health knowledge acquisition
• Evaluated through lab studies and expert interviews for reliability