WhatsApp scheduling boosts message delivery for maternal health chatbot

Window-Aware Scheduling for Health Messaging under Platform Delivery Constraints: Evidence from an AI-Powered WhatsApp Maternal and Infant Health Chatbot in Nigeria

Computation and LanguageComputers and Society

Summary

WhatsApp only lets businesses send free-form messages within 24 hours after a user message; after that, only approved template messages are allowed. The authors studied a maternal health chatbot in Nigeria to see how often messages failed due to this rule. They found message failures jumped sharply right after the 24-hour window closes. They showed that scheduling messages as approved templates after the window closed greatly improved delivery rates compared to waiting or sending prompts. Their findings highlight the importance of respecting WhatsApp's message timing rules to reach users effectively.

What this means in practice

  • For chatbot developers: Optimize health chatbot message timing by using approved templates after the WhatsApp 24-hour messaging window to improve message delivery rates.
  • For customer support teams: Improve automated customer interaction by scheduling messages that comply with WhatsApp platform rules, reducing message failures outside the standard response window.

Authors

Jeremiah Moyondafoluwa Adepoju, Samuel Omolaiye, Thanni Adewuyi, AbdulQahhar Abimbola Okenla, Lily-Aimas Love, Adereni Abiodun

Abstract

WhatsApp lets a business send free-form messages only within 24 hours of a user's last message; outside this customer service window, only pre-approved templates are delivered. Health chatbots inherit this rule, but its cost is rarely measured. We analyse 98,607 messages sent to 3,696 mothers by a WhatsApp maternal health chatbot in Nigeria, with a largely separate export as replication. No free-form message failed with the window open (0 of 35,500), and failure jumped by 93.0 percentage points (95% CI 87.0 to 99.1) at exactly 24 hours. Two flows produced 66.1% of failures, including an offer to speak with a medical professional that, as built, reached 0.3 in 100 mothers whose window had closed. We formalise window-aware scheduling as a decision problem with an action of known zero value. Model-based offline evaluation, with bounds for unconfirmed delivery, estimates that sending the offer as an approved template would reach 81.5 to 86.8 in 100 such mothers, against 16.6 for waiting and 11.6 for a reply prompt. In a calibrated simulation, tabular Q-learning converges to the same template rule and does not beat it in any of 13 stress tests, and opting out does not rise with message volume. The main gain comes from respecting the platform rule, and it needs no learning. All outcomes are deliveries, not health outcomes.
View PDFOpen arXiv