classification text
NaijaSenti
NaijaSenti is the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria — Hausa, Igbo, Nigerian-Pidgin, and Yorùbá — consisting of around 30,000 annotated tweets per language, including a significant fraction of code-mixed tweets.
Domains: SocialWritten
Languages: HausaIgboNigerian PidginYoruba
In benchmark:
- Task type
- Classification
- Main metric
accuracy- Reference
- https://github.com/hausanlp/NaijaSenti
- Source dataset
- mteb/NaijaSenti
- License
- cc-by-4.0
- Dates
- 2022-05-01 → 2023-05-08
- Annotations
- expert-annotated
- Sample creation
- found
Models scored …