README.md

---
license: apache-2.0
base_model: bartpho
tags:
- vietnamese
- aspect-based-sentiment-analysis
- VLSP-ABSA
datasets:
- visolex/VLSP2018-ABSA-Hotel
metrics:
- accuracy
- macro-f1
model-index:
- name: bartpho-absa-hotel
  results:
  - task:
      type: text-classification
      name: Aspect-based Sentiment Analysis
    dataset:
      name: VLSP2018-ABSA-Hotel
      type: VLSP-ABSA
    metrics:
    - type: accuracy
      value: 0.9016
    - type: macro-f1
      value: 0.1161
    - type: macro_precision
      value: 0.2827
    - type: macro_recall
      value: 0.0730
---

# bartpho-absa-hotel: Aspect-based Sentiment Analysis for Vietnamese Reviews

This model is a fine-tuned version of [bartpho](https://huggingface.co/bartpho) 
on the **VLSP2018-ABSA-Hotel** dataset for aspect-based sentiment analysis in Vietnamese reviews.

## Model Details

* **Base Model**: bartpho
* **Description**: BartPho for Vietnamese ABSA
* **Dataset**: VLSP2018-ABSA-Hotel
* **Fine-tuning Framework**: HuggingFace Transformers
* **Task**: Aspect-based Sentiment Classification (3 classes)

### Hyperparameters

* Batch size: `32`
* Learning rate: `3e-5`
* Epochs: `100`
* Max sequence length: `256`
* Weight decay: `0.01`
* Warmup steps: `500`
* Optimizer: AdamW

## Dataset

Model was trained on **VLSP2018 ABSA Hotel dataset** for aspect-based sentiment analysis.

### Sentiment Labels:

* **0 - Negative** (Tiêu cực): Negative opinions
* **1 - Neutral** (Trung lập): Neutral, objective opinions
* **2 - Positive** (Tích cực): Positive opinions

### Aspect Categories:

Model được train để phân tích sentiment cho các aspects sau:

- **FACILITIES#CLEANLINESS**
- **FACILITIES#COMFORT**
- **FACILITIES#DESIGN&FEATURES**
- **FACILITIES#GENERAL**
- **FACILITIES#MISCELLANEOUS**
- **FACILITIES#PRICES**
- **FACILITIES#QUALITY**
- **FOOD&DRINKS#MISCELLANEOUS**
- **FOOD&DRINKS#PRICES**
- **FOOD&DRINKS#QUALITY**
- **FOOD&DRINKS#STYLE&OPTIONS**
- **HOTEL#CLEANLINESS**
- **HOTEL#COMFORT**
- **HOTEL#DESIGN&FEATURES**
- **HOTEL#GENERAL**
- **HOTEL#MISCELLANEOUS**
- **HOTEL#PRICES**
- **HOTEL#QUALITY**
- **LOCATION#GENERAL**
- **ROOMS#CLEANLINESS**
- **ROOMS#COMFORT**
- **ROOMS#DESIGN&FEATURES**
- **ROOMS#GENERAL**
- **ROOMS#MISCELLANEOUS**
- **ROOMS#PRICES**
- **ROOMS#QUALITY**
- **ROOM_AMENITIES#CLEANLINESS**
- **ROOM_AMENITIES#COMFORT**
- **ROOM_AMENITIES#DESIGN&FEATURES**
- **ROOM_AMENITIES#GENERAL**
- **ROOM_AMENITIES#MISCELLANEOUS**
- **ROOM_AMENITIES#PRICES**
- **ROOM_AMENITIES#QUALITY**
- **SERVICE#GENERAL**

## Evaluation Results

The model was evaluated on test set with the following metrics:

* **Accuracy**: `0.9016`
* **Macro-F1**: `0.1161`
* **Weighted-F1**: `0.2486`
* **Macro-Precision**: `0.2827`
* **Macro-Recall**: `0.0730`

## Usage Example

```python
import torch
from transformers import AutoTokenizer, AutoModel

# Load model and tokenizer
repo = "visolex/bartpho-absa-hotel"
tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModel.from_pretrained(repo, trust_remote_code=True)
model.eval()

# Aspect labels for VLSP2018-ABSA-Hotel
aspect_labels = [
    "FACILITIES#CLEANLINESS",
    "FACILITIES#COMFORT",
    "FACILITIES#DESIGN&FEATURES",
    "FACILITIES#GENERAL",
    "FACILITIES#MISCELLANEOUS",
    "FACILITIES#PRICES",
    "FACILITIES#QUALITY",
    "FOOD&DRINKS#MISCELLANEOUS",
    "FOOD&DRINKS#PRICES",
    "FOOD&DRINKS#QUALITY",
    "FOOD&DRINKS#STYLE&OPTIONS",
    "HOTEL#CLEANLINESS",
    "HOTEL#COMFORT",
    "HOTEL#DESIGN&FEATURES",
    "HOTEL#GENERAL",
    "HOTEL#MISCELLANEOUS",
    "HOTEL#PRICES",
    "HOTEL#QUALITY",
    "LOCATION#GENERAL",
    "ROOMS#CLEANLINESS",
    "ROOMS#COMFORT",
    "ROOMS#DESIGN&FEATURES",
    "ROOMS#GENERAL",
    "ROOMS#MISCELLANEOUS",
    "ROOMS#PRICES",
    "ROOMS#QUALITY",
    "ROOM_AMENITIES#CLEANLINESS",
    "ROOM_AMENITIES#COMFORT",
    "ROOM_AMENITIES#DESIGN&FEATURES",
    "ROOM_AMENITIES#GENERAL",
    "ROOM_AMENITIES#MISCELLANEOUS",
    "ROOM_AMENITIES#PRICES",
    "ROOM_AMENITIES#QUALITY",
    "SERVICE#GENERAL"
]

# Sentiment labels
sentiment_labels = ["POSITIVE", "NEGATIVE", "NEUTRAL"]

# Example review text
text = "Khách sạn rất sạch sẽ, phòng ốc thoải mái nhưng giá hơi cao."

# Tokenize
inputs = tokenizer(
    text,
    return_tensors="pt",
    padding=True,
    truncation=True,
    max_length=256
)
inputs.pop("token_type_ids", None)

# Predict
with torch.no_grad():
    outputs = model(**inputs)

# Get logits: shape [1, num_aspects, num_sentiments + 1]
logits = outputs.logits.squeeze(0)  # [num_aspects, num_sentiments + 1]
probs = torch.softmax(logits, dim=-1)

# Predict for each aspect
none_id = probs.size(-1) - 1  # Index of "none" class
results = []

for i, aspect in enumerate(aspect_labels):
    prob_i = probs[i]
    pred_id = int(prob_i.argmax().item())
    
    if pred_id != none_id and pred_id < len(sentiment_labels):
        score = prob_i[pred_id].item()
        if score >= 0.5:  # threshold
            results.append((aspect, sentiment_labels[pred_id].lower()))

print(f"Text: {text}")
print(f"Predicted aspects: {results}")
# Output example: [('aspects', 'positive'), ('aspects', 'positive'), ('aspects', 'negative')]
```

## Citation

If you use this model, please cite:

```bibtex
@misc{visolex_absa_bartpho_absa_hotel,
  title={BartPho for Vietnamese ABSA for Vietnamese Aspect-based Sentiment Analysis},
  author={ViSoLex Team},
  year={2025},
  url={https://huggingface.co/visolex/bartpho-absa-hotel}
}
```

## License

This model is released under the Apache-2.0 license.

## Acknowledgments

* Base model: [bartpho](https://huggingface.co/bartpho)
* Dataset: VLSP2018-ABSA-Hotel
* ViSoLex Toolkit

---