Projects

SMS survey on emerging risks amongst vulnerable populations (2011)

PARTNERS: Question Box

PROGRAMME AREA: Economic Well-being

LAB: New York

SUMMARY:

Global Pulse has partnered with Question Box to test the potential of using search queries to identify emerging risks amongst vulnerable populations at a local level. The findings of this analytical assessment will be used as a test case for real time query based tracking of potential risks to vulnerable populations. In the long term, monitoring of anonymised query data may be able to provide local and macro indicators of emerging risks to the vulnerable.

Question Box is a facility that allows people who generally have no access to the internet to make queries of a remote team. People can make the queries through a custom constructed device similar to a pay phone. Question Box Operators identify answers through internet search queries, databases of relevant local information and answers to previous questions. The answer is generally quickly identified and operators then translate it back into the local language. To improve accessibility the service could be extended in the future to support SMS queries in addition to voice. Voice service is currently operational in Uganda and India and has received thousands of queries. Many of the queries relate to agriculture and health although there are a wide range of questions about employment, business, politics, sport and other interests. Global Pulse is analysing an anonymised database of question box queries to explore the timing, frequency and type of queries.

This assessment should identify trends in the queries that provide strong indicators about events occurring at a local level. These indicators will then be retrospectively compared against recorded events. It is expected that queries will be correlated with events and trends in the study communities. For example, an increase in queries about jobs may indicate rising unemployment, queries about particular crop symptoms may be correlated with an outbreak of agricultural disease and/or queries about government assistance may indicate increase household vulnerability. This non-traditional form of data capture also has additional advantages including building local resilience by assisting vulnerable people with targeted information and avoiding incentives to "game" the system that may exist in compensated surveys. Finally in the long term communities may even be willing to pay for the service, making it self sustaining.