metadata
language:
- en
- ny
- bem
tags:
- sentiment-analysis
- multilingual
- transformer
- zambia
- lusaka
- bemba
- icibemba
- nyanja
- icinyanja
license: apache-2.0
library_name: transformers
pipeline_tag: text-classification
base_model:
- Kelvinmbewe/mbert_Lusaka_Language_Analysis
- google-bert/bert-base-multilingual-cased
metrics:
- accuracy
- precision
- recall
- f1
- confusion_matrix
- validation_loss
model-index:
- name: LusakaLang
results:
- task:
type: text-classification
name: Sentiment Analysis
dataset:
name: LusakaLang Training Data
type: lusakalang
config: default
split: test
metrics:
- type: accuracy
value: 0.9322
name: accuracy
- type: f1
value: 0.9216
name: f1_macro
- type: f1
value: 0.8649
name: f1_negative
- type: f1
value: 0.95
name: f1_neutral
- type: f1
value: 0.95
name: f1_positive
- type: loss
value: 0.4025
name: test_loss
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
