WaLLM -- Insights from an LLM-Powered Chatbot deployment via WhatsApp

2025-05-13

AI Summary

To address low generative AI accessibility in developing countries due to the digital divide, this work proposes and deploys WaLLM—a WhatsApp-native, lightweight large language model (LLM) service architecture optimized for low-bandwidth environments. Methodologically, WaLLM integrates a quantized LLM API, the WhatsApp Business Platform interface, log-driven behavioral analytics, and an intent recognition module, complemented by culturally adapted, incentive-based interaction design—including daily trending questions, intelligent follow-up suggestions, topic trend analysis, and a gamified point leaderboard. Over six months, WaLLM served ~100 users, processing 14,700 queries; 55% were factual queries, with “health and well-being” constituting 28% of all topics. Users engaging with the leaderboard exhibited threefold higher activity than non-users. This work contributes a reproducible technical framework and human-centered design paradigm for AI democratization in resource-constrained settings.

Technology Category

• Humans and AI: AI for Accessibility
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Recent advances in generative AI, such as ChatGPT, have transformed access to information in education, knowledge-seeking, and everyday decision-making. However, in many developing regions, access remains a challenge due to the persistent digital divide. To help bridge this gap, we developed WaLLM - a custom AI chatbot over WhatsApp, a widely used communication platform in developing regions. Beyond answering queries, WaLLM offers several features to enhance user engagement: a daily top question, suggested follow-up questions, trending and recent queries, and a leaderboard-based reward system. Our service has been operational for over 6 months, amassing over 14.7K queries from approximately 100 users. In this paper, we present WaLLM's design and a systematic analysis of logs to understand user interactions. Our results show that 55% of user queries seek factual information."Health and well-being"was the most popular topic (28%), including queries about nutrition and disease, suggesting users view WaLLM as a reliable source. Two-thirds of users' activity occurred within 24 hours of the daily top question. Users who accessed the"Leaderboard"interacted with WaLLM 3x as those who did not. We conclude by discussing implications for culture-based customization, user interface design, and appropriate calibration of users' trust in AI systems for developing regions.

Problem

• Bridging digital divide via WhatsApp-based AI chatbot
• Enhancing user engagement with interactive features
• Analyzing user interactions in developing regions

Innovation

• WhatsApp-based AI chatbot for developing regions
• Features: daily questions, follow-ups, leaderboard rewards
• Analyzed user interactions for cultural customization