New PhD study to detect multilingual AI misinformation

Now, a groundbreaking PhD study is stepping into that gap, developing artificial intelligence capable of detecting misinformation in isiZulu and Sepedi alongside English, which could become critical in the fight against digital deception. The research, led by University of Pretoria Dr Seani Rananga, who’s a PhD student at the North West University, comes at a time when AI-generated content, including manipulated images, misleading posters and fabricated messaging, is becoming harder to identify, even for experienced users. “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,” Dr Rananga said.

This leaves speakers of indigenous languages at a disadvantage when it comes to identifying false or misleading information online. Her study demonstrates demonstrates that multilingual AI can identify misleading information across the three languages while highlighting the importance of improving machine translation for low-resource African languages. The study provides a framework that can be adapted to combat misinformation during elections, public emergencies and other events where false information can have serious consequences.

Dr Rananga said the research 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 misinformation. The urgency is clear. From election campaigns to public health messaging, misinformation has the power to influence behaviour, fuel panic and erode trust. The Covid-19 pandemic used as a test case in the study showed just how quickly false claims can spread and how damaging they can be when left unchecked.