Nabibia's picture
Update README.md
45355b5 verified
|
Raw History Blame Contribute Delete
1.98 kB
---
language:
- sw
- en
tags:
- text-classification
- depression-detection
- swahili
- sheng
- hybrid-model
- afriberta
library_name: pytorch
---
# Hybrid AfriBERTa for Swahili/Sheng Depression Detection
This model is a custom hybrid neural network designed to detect depressive language patterns in code-mixed Swahili and Sheng social media posts, specifically among Kenyan university students.
## Model Details
- **Developed by:** Peter Nabibia (Meru University of Science and Technology)
- **Supervisors:** Dr. Amos Chege Kirongo, Dr. Mary Mwadulo. (Meru University of Science and Technology)
- **Model type:** Hybrid Transformer + MLP (Late Fusion)
- **Language(s):** Swahili, Sheng (Code-mixed)
- **License:** Apache 2.0
## Architecture
The model fuses two distinct text analysis techniques:
1. **Emotion Analysis:** A pre-trained **AfriBERTa** transformer extracts a 768-dimensional `[CLS]` token embedding to capture holistic contextual semantics.
2. **Linguistic Feature Analysis:** An MLP processes 4 engineered psycholinguistic features (First-person pronouns, negative words, absolutist words, lexical diversity) into a 32-dimensional vector.
These branches are concatenated (800 dimensions) and passed through a fully connected layer with Softmax for binary classification.
## Performance
Evaluated on a balanced held-out test set of 353 Swahili/Sheng tweets:
- **Accuracy:** 96.88%
- **Precision:** 95.73%
- **Recall:** 99.02%
- **F1-Score:** 97.35%
- **AUROC:** 99.30%
## Intended Use & Limitations
**Clinical Disclaimer:** This model is a research prototype. It is NOT a clinical diagnostic tool. Predictions should not be used for real-time screening, triage, or medical diagnosis. Any real-world deployment must be accompanied by human oversight from licensed mental health professionals.
## Training Data
The model was trained on the [Swahili/Sheng Depression Corpus](https://huggingface.co/datasets/Nabibia/swahili-sheng-depression-corpus) (3,522 tweets).