Instructions to use Tobias/bert-base-german-cased_German_Hotel_sentiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tobias/bert-base-german-cased_German_Hotel_sentiment with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Tobias/bert-base-german-cased_German_Hotel_sentiment")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Tobias/bert-base-german-cased_German_Hotel_sentiment") model = AutoModelForSequenceClassification.from_pretrained("Tobias/bert-base-german-cased_German_Hotel_sentiment", device_map="auto") - Notebooks
- Google Colab
- Kaggle
German Hotel Review Sentiment Classification
A model trained on German Hotel Reviews from Switzerland. The base model is the bert-base-german-cased. 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 |
|---|---|---|---|
| Positive | 90.48% | 82.61% | 86.36% |
| Negative | 70.59% | 92.31% | 80.00% |
| Neutral | 28.57% | 13.33% | 18.18% |
| Accuracy | 76.00% | ||
| Macro Average | 63.21% | 62.75% | 61.52% |
| Weighted Average | 73.43% | 76.00% | 73.65% |
Confusion Matrix
- Downloads last month
- 59
