Radiolytica

In humanitarian crises, the spread of misinformation, disinformation, and hate speech can cause real-world harm, undermining public health efforts and threatening the safety of both affected populations and aid workers. While digital tools have been developed to detect such content online, they are largely unsuitable for many humanitarian contexts in sub-Saharan Africa, where internet penetration is low and the vast majority of people rely on radio as their most trusted source of news. Despite its influence, humanitarian organisations face significant logistical hurdles in monitoring radio due to language diversity, the absence of fixed broadcasting schedules, and a lack of automated tools for offline audio.

This project aims to fill this gap by developing an AI-powered system that records and transcribes community radio broadcasts in Swahili and French into written English. Using the Eastern Democratic Republic of Congo (DRC) as a primary case study, we leverage Natural Language Processing and generative AI to investigate the extent of misinformation broadcast on community radio, with a particular focus on health and epidemics. By identifying peak periods and key themes of misinforming content, the project provides actionable insights that allow for targeted humanitarian countermeasures.

Furthermore, to inform which forms of journalism support are most effective at protecting vulnerable communities, we examine how the timing and extent of humanitarian-affiliated radio content shapes the broader information environment. Ultimately, this project seeks to establish a scalable monitoring system that enables humanitarian organisations to respond to misinformation with timely fact-checking and pre-emptive counter-narratives, safeguarding the integrity of humanitarian efforts.