WangchanBERTa for Thai Restaurant ABSA
Fine-tuned WangchanBERTa for Aspect-Based Sentiment Analysis (ABSA) on Thai restaurant reviews.
Model Description
This model classifies sentiment across 10 aspects simultaneously from a single Thai restaurant review. It was fine-tuned as part of a Computer Science Senior Project at Kasetsart University (2025).
Aspects & Labels
10 Aspects:
taste · food_quality · portion · atmosphere · cleanliness ·
location_parking · staff · speed · price · value
4 Sentiment Labels:
positive · neutral · negative · not_available
not_available means the aspect was not mentioned in the review.
Training Details
| Base Model | airesearch/wangchanberta-base-att-spm-uncased |
| Dataset | Wongnai Restaurant Review Dataset (19,938 reviews) |
| Labeling | LLM-Assisted Labeling via gpt-4.1-mini |
| Architecture | Transformer Encoder → Mean Pooling → 10 × Linear(768→4) |
| Optimizer | AdamW · Weight Decay = 0.01 |
| Learning Rate | 3.84e-05 |
| Warmup Ratio | 0.081 |
| Dropout | 0.111 |
| Batch Size | 8 |
| Max Epochs | 10 (Early Stopping Patience = 3) |
| Best Epoch | 7 |
| Loss | Weighted Cross-Entropy · Class Weight Cap = 15.0 |
| Precision | Mixed Precision (FP16) |
Performance (Test Set)
| Aspect | Macro-F1 |
|---|---|
| taste | 0.7415 |
| food_quality | 0.6388 |
| portion | 0.6340 |
| atmosphere | 0.7104 |
| cleanliness | 0.7498 |
| location_parking | 0.7245 |
| staff | 0.7324 |
| speed | 0.7209 |
| price | 0.7189 |
| value | 0.6000 |
| Overall | 0.6971 |
Usage