German Hotel Review Sentiment Classification
A model trained on English Hotel Reviews from Switzerland. The base model is the bert-base-uncased. The last hidden layer of the base model was extracted and a classification layer was added. The entire model was then trained for 5 epochs on our dataset.
Model Performance
| Classes | Precision | Recall | F1 Score |
|---|---|---|---|
| Room | 77.78% | 77.78% | 77.78% |
| Location | 95.45% | 95.45% | 95.45% |
| Staff | 75.00% | 93.75% | 83.33% |
| Unknown | 71.43% | 50.00% | 58.82% |
| HotelOrganisation | 27.27% | 30.00% | 28.57% |
| Food | 87.50% | 87.50% | 87.50% |
| ReasonForStay | 63.64% | 58.33% | 60.87% |
| GeneralUtility | 66.67% | 50.00% | 66.67% |
| Accuracy | 74.00% | ||
| Macro Average | 70.59% | 67.85% | 68.68% |
| Weighted Average | 74.17% | 74.00% | 73.66% |
Confusion Matrix
- Downloads last month
- 16
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.