By Zuko Komisa

- Dr Seani Rananga’s North-West University PhD study has introduced a multilingual AI framework to detect online misinformation across English, isiZulu, and Sepedi.
- The research addresses the digital gap for low-resource African languages, offering vital tools to combat false information during elections, health crises, and public emergencies.
- Honoured with a prestigious Google PhD Fellowship, Dr Rananga plans to expand the project to cover more indigenous languages and counter threats like deepfakes and hate speech.
While artificial intelligence (AI) frequently aids in identifying false information online in English, indigenous South African languages have long lacked effective detection tools.
A groundbreaking doctoral study by Dr Seani Rananga at North-West University (NWU) is bridging this divide by developing multilingual AI capable of spotting misinformation in English, isiZulu, and Sepedi.
Dr Rananga, now a lecturer at the University of Pretoria, used Covid-19 health claims as an initial pilot case.
Her findings demonstrate that while multilingual AI can reliably identify misleading content, improving machine translation quality remains crucial for low-resource African languages.
Highlighting the necessity of the project, Dr Rananga noted:
“South Africa is one of the most linguistically diverse countries in the world, yet most AI systems for detecting misinformation are developed primarily for English. This leaves speakers of indigenous languages at a disadvantage when it comes to identifying false or misleading information online.”
The research offers an adaptable framework designed to assist government bodies, fact-checking agencies, and social media platforms in curbing harmful narratives during elections and national emergencies.
The project’s global significance earned Dr Rananga a prestigious Google PhD Fellowship and the Best Poster Award at the 2025 Deep Learning IndabaX South Africa.
Looking ahead, Dr Rananga intends to broaden the framework to include additional South African languages while tackling emerging digital threats, such as AI-generated deepfakes and online hate speech.
Her ultimate aim is to ensure African languages are fully integrated into future AI developments, fostering safer and more inclusive digital environments.
READ NEXT: Mamelodi Regional Hospital celebrates major surgical breakthrough