Using Machine Learning to Analyse Radio Content in Uganda

In a world of increasing interconnectivity, radio remains a primary source of information for communities in many parts of the world, including Uganda. Radio reaches large groups of people in real-time and is often a medium for community discussions on subjects like healthcare, education, the provision of services and even politics. There is a wealth of data that can be extracted from public radio conversations and these data can be parsed to support sustainable development and humanitarian efforts. Insights about the spread of infectious diseases, or the way people move during a disaster, or how they perceive healthcare campaigns or access to jobs and education, can be derived from radio talk. This report outlines the methodology and processes of the Radio Content Analysis Tool, a prototype developed by Pulse Lab Kampala to analyse public radio content in Uganda and explore its value for informing the development of UN projects and programmes on the ground. It distils the technology behind the creation of the Radio Content Analysis Tool and presents the lessons learned along the way. The report also details the results of several pilot studies that were conducted together with partners from the Government, UN agencies and academia to understand the validity and value of unfiltered public radio discussions for development.