LLMs Spot Social Challenges in South African Languages
Can AI help governments hear the public—across languages? This new study tests large language models (LLMs) on South African social media, analyzing sentiment on the top 10 emerging topics in English, Sepedi, and Setswana.
- What they tested: GPT-3.5, GPT-4, Llama 2, PaLM 2, and Dolly 2 in zero-shot mode.
- Where: Posts tied to 10 South African government departments.
- Key finding: Big differences across models, topics, and languages.
- Breakthrough: Fusing model outputs (an ensemble) cut reported errors to under 1%.
- So what: Reliable, multilingual sentiment signals can now flag social challenges early and guide targeted action.
Paper: https://arxiv.org/abs/2511.17301v1
Note: Any real-world rollout should protect privacy and include human oversight.
Paper: https://arxiv.org/abs/2511.17301v1
Register: https://www.AiFeta.com
#AI #LLM #SentimentAnalysis #SouthAfrica #MultilingualAI #GovTech #PublicPolicy #SocialMedia #Sepedi #Setswana
