In low and middle income countries, ICT4D interventions have been used to improve outcomes in sectors such as health, agriculture, and education. Several such interventions are designed using Interactive Voice Response or IVR. This is done to ensure more inclusion towards people who do not have access to any other forms of technology beyond simple mobile phones and who are not literate enough to consume and produce textual forms of information.
Scalable development impact is a central challenge in the ICT4D communities, and lack of scale is often cited as one of the main reasons for little impact in the face of big challenges. In contrast, certain IVR services designed around the theme of entertainment and social-networking for similarly low-income, low-literate audiences have scaled to tens of thousands of users with little to no advertisement cost for user acquisition.
Such services can be leveraged to advertise and spread core development-related services. An Empirical Comparison of Technologically Mediated Advertising in Under-connected Populations compares the effectiveness of leveraging an IVR entertainment service as a user acquisition strategy for a large scale development service against conventional advertisement channels.
Super Abbu Service for Expectant Fathers
Super Abbu (Super Dad), is an IVR-based development service that allows expectant fathers to ask questions and get answers from doctors, listen to publicly-posted questions and (doctors’) answers, and share relevant personal stories with peers.
Super Abbu is specifically targeted towards low-literate expectant fathers as pregnancy and childbirth remain taboo topics among men in Pakistan where maternal and child health indicators remain exceptionally poor. Traditional maternal health information services for mothers often fail to achieve desired outcomes as women are not the primary decision makers in most Pakistani households.
As part of a country-wide roll out of Super Abbu in Pakistan, we needed to reach a large number of users who would find the service relevant. Acquiring (and training) users is a significant challenge for any development service, particularly among under-connected populations. Moreover, the ability to effectively advertise to a large number of people directly impacts the scalability of the service.
Customer Acquisition for Super Abbu
While traditional media such as paper flyers, public posters, television and radio advertisements have been used to market to low income users, over the past decade with the rapid proliferation of mobile phones, mobile marketing mechanisms such as robocalls have become more common.
More recently, low-cost Android phones and subsidized access to mobile Internet have made digital marketing through sponsored ads on online social networks a possibility. This paper presents results from an 11 week campaign where we acquired users for Super Abbu through seven different advertising channels:
- paper flyers
- banners displayed at the back of auto rickshaws
- cable TV ads
- radio ads
- robocalls
- sponsored Facebook ads
- an IVR-based entertainment service.
Across these channels we eventually reached 21,770 users who engaged in 32,625 interactions on Super Abbu. To assess the efficacy of the channels, we considered three main user acquisition metrics: conversion rate, cost of user acquisition, and retention rate. Furthermore, to understand whether the IVR users interact with Super Abbu differently from users acquired through other channels, we compared users in terms of their activity, engagement, and IVR use sophistication.
Overall, our results show that the IVR-based entertainment service outperformed other advertising channels on all considered user acquisition metrics with the exception of robocalls, which lead in terms of spread.
The Power of Polly IVR Service
Polly, one of the advertisement services that we used to spread and scale Super Abbu, is an IVR-based entertainment service designed to reach low-literate, low-income populations via a simple voice-based game. When users call Polly, they are able to record and send voice messages to their friends in morphed, funny voices, making Polly playful while also providing a utility of being able to send free voice messages. This allows users to
- Be introduced to Polly through a referral from a friend whom they trust
- Immediately identify the playful aspect of Polly after answering the call.
Our work tries to replicate Polly’s success to promote a different development service. One of our key findings is the surprisingly high conversion rates for Polly (50%) and robocalls (25%) compared to other channels (less than 0.1%). The latter statistics are not surprising, as the industry standard for advertisement channels is also 0.1%.
While our data does not establish the causal reasons for the high conversion rates of Polly and robocalls, we can hypothesize several explanations.
- The high conversion rate of Polly might be due to its entertainment value that lowers the barrier for the users to press a button and explore the advertised service.
- Both robocalls and Polly employ the same modality (IVR) as the development service.
This allows a relatively smooth transition between the advertisement channel and the advertised service compared to other channels where people need to memorize the advertised phone numbers and dial them later. This means a higher cognitive load and persistent motivation compared to simply pressing a key immediately on Polly and robocalls.
The IVR advertisement services also offer a smoother transition in terms of pre-training or at least priming the users to navigate speech interfaces before transitioning to the development service. Previous work supports this hypothesis as it has been shown that speech-based entertainment services implicitly train users to better handle speech interfaces.
Yet another reason for the high conversion rate of robocalls could be that these calls were made to users of government-run information services (health and agriculture), so they may be primed and pre-selected to be more open to such services given that they had volunteered their phone numbers.
IVR Beats Facebook & Other Advertising
Our findings point to IVR platforms (robocalls and Polly in our study) performing better than other platforms (Facebook, flyers, radio, cable TV and rickshaw ads) in terms of user acquisition.
Users acquired through the IVR entertainment service (Polly) performed better than other channels in all interface-related measures (activity, feature engagement, use of sophisticated interface features, and retention). Only robocalls, Facebook, and the entertainment service were able to acquire users at relatively low cost per user (around $1 or less).
In contrast, most users acquired from outside of the entertainment service did not end up becoming long-term users of the development service. Our findings also show the comparatively lower performance of increasingly popular social media advertisement platforms (Facebook) to recruit low-income users (91 out of 102,935 people reached).
A lightly edited synopsis of An Empirical Comparison of Technologically Mediated Advertising in Under-connected Populations by Mustafa Naseem, Bilal Saleem, Sacha Ahmad, Jay Chen, and Agha Ali Raza
Sorry, the comment form is closed at this time.