用有温度的对话AI提升低识字率群体调查参与度
Improving Survey Participation in Low-Literacy Populations Through Value-Sensitive Conversational AI
- 设计贴近文化背景的对话式AI，降低沟通门槛
- 完整融入价值敏感设计后完成率达92%，流失率最低
- 适合关注公平、包容性数据收集的研究者与公益项目
从低识字率群体获取可靠社会数据仍是难题，尤其涉及敏感话题和边缘群体时。传统纸质与网页问卷常因识字障碍、社会压力和互动不适导致高流失与不完整回答。本文基于对印度315名低识字女性的实地评估，对比了纸质访谈、数字网页调查、对话式AI（convAI）以及融合多层次价值敏感设计的convAI。结果表明，集成价值敏感设计的convAI显著提升问卷完成率，其完成率最高、流失率最低。研究证明，以人为本、注重价值的交互设计对实现包容、伦理且可扩展的数据采集至关重要，推动更多‘AI向善’应用落地。
原文摘要 · Abstract (English)
Collecting reliable social data from low-literacy populations remains a persistent challenge, particularly when surveys involve sensitive topics and marginalized communities. Traditional paper-based and web-based survey modalities often suffer from high attrition and incomplete responses due to literacy barriers, social pressure, and interactional discomfort. In this paper, we present findings from an initial field evaluation comparing multiple survey modalities paper-based interviews, digital web-based surveys, conversational AI (convAI) surveys, and convAI enhanced with layered value-sensitive design conducted with low-literacy women across India. Using data from 315 participants, we show that convAI significantly improves survey completion rates relative to traditional modalities, with the highest completion and lowest drop-off observed when value-sensitive and culturally aligned conversational design elements are fully integrated. These results demonstrate the importance of human-centered and value-sensitive interaction design in enabling inclusive, ethical, and scalable data collection; motivating more `AI for social good' applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。