AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages
AfriSenti is the largest sentiment analysis dataset for under-represented African languages, covering 110,000+ annotated tweets in 14 African languages (Amharic, Algerian Arabic, Hausa, Igbo, Kinyarwanda, Moroccan Arabic, Mozambican Portuguese, Nigerian Pidgin, Oromo, Swahili, Tigrinya, Twi, Xitsonga, and Yoruba).
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Zero-shot Sentiment Classification | SACL-XLMR | UCAS-IIE-NLP at SemEval-2023 Task 12: … | 2023-06-01 |
| Zero-shot Sentiment Classification | AfroXLMR | UCAS-IIE-NLP at SemEval-2023 Task 12: … | 2023-06-01 |
| Zero-shot Sentiment Classification | AfriBERTa | UCAS-IIE-NLP at SemEval-2023 Task 12: … | 2023-06-01 |
| Zero-shot Sentiment Classification | XLM-R | UCAS-IIE-NLP at SemEval-2023 Task 12: … | 2023-06-01 |
| Zero-shot Sentiment Classification | Random | UCAS-IIE-NLP at SemEval-2023 Task 12: … | 2023-06-01 |
Recent papers with results on this dataset: