LusakaLang Sentiment Analysis Model
This model is trained on mbert_Lusaka_Language_Analysis a predecessor model that was fine‑tuned to interpret
English, Bemba, Nyanja, Zambian slang and mixed Zambian language varieties frequently encountered in everyday communication.
The model captures:
- Zambian English idioms
- Bemba and Nyanja language nuances
- Mixed‑languages or slang
- Indirect emotional expressions commonly used in Zambian.
Training Data
The training dataset was derived from AI‑generated synthetic sources and subsequently reviewed by a native Zambian speaker to ensure linguistic accuracy, cultural appropriateness, and overall data quality.
Classification and Loss
Training and Validation Loss
Confusion Matrix
Word Cloud
- Downloads last month
- 94
Model tree for Kelvinmbewe/mbert_LusakaLang_Sentiment_Analysis
Base model
google-bert/bert-base-multilingual-casedEvaluation results
- accuracy on LusakaLang Training Datatest set self-reported0.932
- f1_macro on LusakaLang Training Datatest set self-reported0.922
- f1_negative on LusakaLang Training Datatest set self-reported0.865
- f1_neutral on LusakaLang Training Datatest set self-reported0.950
- f1_positive on LusakaLang Training Datatest set self-reported0.950
- test_loss on LusakaLang Training Datatest set self-reported0.403