Groundbreaking AI study combats misinformation in South African indigenous languages

Dr Seani Rananga has received global recognition for a study that has developed multilingual AI to detect false information.

For too long, African languages have been underrepresented in artificial intelligence (AI), but this could soon be a thing of the past as a recent PhD study by North-West University has developed AI tools to detect misinformation in South African languages.

This follows research by Dr Seani Rananga, a lecturer in the Department of Computer Science at the University of Pretoria, which demonstrated that multilingual AI can identify misleading information across IsiZulu, English and Sepedi.

Her PhD research, which she completed at North-West University, focused on artificial intelligence, natural language processing, multilingual AI, and misinformation detection in African languages, and has received global recognition. She used misinformation surrounding the Covid-19 pandemic as a pilot case study to test the multilingual framework.

Rananga said the study was driven by the need to ensure that speakers of South Africa’s indigenous languages are not left behind as AI becomes increasingly important in identifying false information.