Engaging Pregnant Women in Kenya with a Hybrid Computer-Human SMS Communication System

Abstract

A growing body of HCI4D research studies the use of SMS communication to deliver health and information services to underserved populations. This paper contributes a novel dimension to this field of study by examining if a hybrid computer-human SMS system can engage pregnant women in Kenya in health-related communication. Our approach leverages the different strengths of both the computer and the human. The computer automates the bulk-sending of personalized messages to patients, allowing the human to read patients' replies and respond to those in need of attention. Findings from a 12-month deployment with 100 women show that our approach is capable of engaging the majority of participants in health-related conversations. We show that receiving messages from the system triggers participant communication and the amount of communication increases as participants approach their expected due date. In addition, analysis of participants' messages shows that they often contain sensitive health information conveyed through a complex mixture of languages and 'txting' abbreviations, all of which highlight the benefits of including a human in the workflow. Our findings are relevant for HCI researchers and practitioners interested in understanding or engaging underserved populations.

Mobile Phones as Amplifiers of Social Inequality among Rural Kenyan Women

“…The second author then translated and transcribed recordings from the sessions. Upon returning to U.S., the first author adopted an iterative, inductive approach typical in anthropology, thereby pairing an understanding of participants' worldviews with prior research in HCI [Medhi et al 2011;Perrier et al 2015] and critical perspectives drawn from ideas from the amplification theory [Toyama 2011[Toyama , 2015, and postcolonial computing [Dourish and Mainwaring 2012;Irani et al 2010] when analyzing transcripts; specifically, she looked for frequent and consistent instances in the data that revealed a mismatch between our respondents' capabilities and Safaricom's products and services. This analysis involved reading transcripts four times, and coding them to identify similarities among participants and their mobile phone use experiences [Strauss and Corbin 1998].…”

“…"Safe Mathare" is another prototype application developed for Kenyans, with the specific purpose of helping protect female Nairobi slum-dwellers from crime at night by "find(ing) trusted others to accompany them as they walk around the slum" [Hagan et al 2012]. More recent HCI interventions include Perrier et al's development of a novel "hybrid computer-human SMS system" that provides pregnant women in urban Kenya with health information [Perrier et al 2015].…”

“…In most cases, their developers recognize that, for these projects to have their intended impact, they must scale to reach populations beyond the small numbers of research participants on which these studies are based (see Perrier et al [2015]). However, as Zuckerman observes [Zuckerman 2010], "Truly revolutionary applications (.…”

Syrian Refugees and Digital Health in Lebanon

“…Audio recorded advice would then be sent accordingly. SMS has also been used to send bulk messages about maternal health to women, for example, by allowing clients to send messages to a nurse who would then respond with more personalized messages [27]. Additional systems have been designed to support social workers in identifying high risk pregnancies, including a mobile phone application that allows data collection, such as registration information for new cases, and follow-up meetings between social workers and women in rural areas [2].…”

“…Furthermore, any attempt to bridge communication between the formal health providers and the informal networks within ITSs is likely to face a number of organizational and political barriers, and these would be best addressed through the active involvement of NGOs and the MoPH in the design process. There has been success in linking healthcare providers to patients in Kenya, where the system allows for nurses to respond to text messages sent by women [27]. Likewise, models similar to those that use voice based technologies for health in rural India [18,33] should be explored; and extended to take account of the women's preference for the use of WhatsApp voice notes.…”