Downloads · 30 days
4
10% of all-time downloads
roberta-postoperative-sentiment-healthcare
crich011/roberta-postoperative-sentiment-healthcare
roberta-postoperative-sentiment-healthcare is a machine learning model from crich011. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
- Base model: cjen1008/distilroberta-healthcare-sentiment - Task: 3-class sentiment classification - Labels: negative, mixed/neutral, positive, assigned by two physicians training as orthopedic surgeons
All-time downloads
42
Public
Parameters
82.1M
328 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors328 MB · 99%
At a glance
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026
- SHA
- 59efc46b
Model card
From the Hugging Face model README
Postoperative Patient Sentiment
Model Details
- Base model:
cjen1008/distilroberta-healthcare-sentiment - Task: 3-class sentiment classification
- Labels:
negative,mixed/neutral,positive, assigned by two physicians training as orthopedic surgeons
Intended Use
Sentiment classification of postoperative patient comments from spine and arthroplasty cohorts for research and quality-improvement workflows.
Training
- Fine-tuning set: 400 comments total (200 spine, 200 arthroplasty)
- Hyperparameters: 4 epochs, learning rate
2e-5, batch size8(train) /16(eval), max length256
Evaluation (Holdout)
| Cohort | n | Macro F1 | Weighted F1 | Accuracy |
|---|---|---|---|---|
| Spine | 205 | 0.687353 | 0.747496 | 0.746341 |
| Arthroplasty | 191 | 0.744606 | 0.788168 | 0.801047 |
Limitations
- Developed in a specific institutional context; external generalization is not guaranteed.
- Labels are based on human rater judgments and may reflect rater variability.
- Not intended as a standalone clinical decision tool.
- Type
- roberta
- License
- mit
- Languages
- en
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026