# WASHtsApp -- A RAG-powered WhatsApp Chatbot for supporting rural African clean water access, sanitation and hygiene

arXiv: https://arxiv.org/abs/2411.02850 · HTML: https://mlsanity.com/paper/2411.02850/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 21 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 4 of 4)

- [A Complete Survey on LLM-based AI Chatbots](https://mlsanity.com/paper/2406.16937/) (2024)
- [Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge](https://mlsanity.com/paper/2403.01432/) (2024)
- [Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.18676/) (2024)
- [New Curriculum, New Chance -- Retrieval Augmented Generation for Lesson Planning in Ugandan Secondary Schools. Prototype Quality Evaluation](https://mlsanity.com/paper/2408.07542/) (2024)

## Abstract (arXiv)

This paper introduces WASHtsApp, a WhatsApp-based chatbot designed to educate rural African communities on clean water access, sanitation, and hygiene (WASH) principles. WASHtsApp leverages a Retrieval-Augmented Generation (RAG) approach to address the limitations of previous approaches with limited reach or missing contextualization. The paper details the development process, employing Design Science Research Methodology. The evaluation consisted of two phases: content validation by four WASH experts and community validation by potential users. Content validation confirmed WASHtsApp's ability to provide accurate and relevant WASH-related information. Community validation indicated high user acceptance and perceived usefulness of the chatbot. The paper concludes by discussing the potential for further development, including incorporating local languages and user data analysis for targeted interventions. It also proposes future research cycles focused on wider deployment and leveraging user data for educational purposes.