A crowdsourced local news platform for Uganda

Abstract

This report presents the design, development, and implementation strategy for a crowdsourced local news platform specifically tailored for Uganda. The main goal is to fill the gap in reliable news especially in rural areas where access is often limited. Our platform aims to give communities more say in what gets reported while making sure the news is accurate and trustworthy by blending Artificial Intelligence (AI) with blockchain technology. Core Features and Strategy: At the core of it all is a strong verification system. AI tools help us fact-check stories and confirm that the content is genuine. Meanwhile, blockchain keeps a transparent, unchangeable record of all approved news, building confidence across users. Customized for Uganda: • Multimedia Support: Support for various media (text, photos). • Gamification: Features that motivate community members to contribute high-quality content. • Localized Filtering: Users can filter news feeds based on where they are and what interests them. Overcoming Challenges The verification process is automated and optimized, combining machine learning with community input for quick, reliable results. We also dive into some of the biggest obstacles, such as: • The need for local data to train AI models effectively. • Ensuring verification works well even with poor internet connections. • Keeping users engaged over time. This project marks a major leap forward in giving Ugandan communities the tools to access and share trustworthy local news, laying the groundwork for grassroots journalism. The tech and strategies we're developing could be a model for other regions around the world facing similar challenges around getting reliable information. News Classification The news will be classified into three critical types: • Verified: Content verified as factual and accurate. • Fake: Content containing false or misleading information. • Propaganda: Content designed to influence opinions or behaviors through biased or misleading reporting.