Dual-Source Retrieval-Augmented Generation Chatbot for Women’s Health (HerCare): Design and Multimethod Evaluation Study
Kimia Tuz Zaman, Wordh Ul Hasan, Nova Ahmed, Juan Li · 2026
Read Dual-Source Retrieval-Augmented Generation Chatbot for Women’s Health (HerCare): Design and Multimethod Evaluation Study by Kimia Tuz Zaman, Wordh Ul Hasan, Nova Ahmed, Juan Li (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13427079.txt.
Description
Zaman and colleagues built and field-tested in 2026 HerCare, a women's health chatbot. It answers from two sources at once, expert medical knowledge and peer stories, and shows the source of each answer. Health chatbots tend to be either dry and clinical or warm but unreliable. Showing where an answer comes from is meant to let users judge trust for themselves.
In a single-session online study, 243 women completed the test. Usability scores ran high, and seven in ten users said they would recommend it. Text analysis found the bot's tone stayed warmly positive even when users wrote in distress. It followed a validate-then-guide pattern: first naming the feeling, then steering to advice.
Catalog record
| CREATOR | Kimia Tuz Zaman, Wordh Ul Hasan, Nova Ahmed, Juan Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |