Preangkwan's picture
Update README.md
136141a verified

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