Update README.md

README.md

@@ -1,3 +1,38 @@
 ---
+language: eng
+tags:
+- bert
 license: apache-2.0
+
+widget:
+- text: "Das Frühstück ist sehr gut, es gibt auch Laktosefreie Produkte."
+  example_title: "Example 1"
+- text: "Das Personal ist sehr kompetent und sehr freundlich."
+  example_title: "Example 2"
+- text: "Die Zimmer sind wie beschrieben sehr klein, vergleichbar mit einer Kreuzfahrtschiffkabine. "
+  example_title: "Example 3"
+- text: "Scheinwerfer vor dem Zimmer ganze Nacht an und zu hell"
+  example_title: "Example 4"
 ---
+
+# German Hotel Review Sentiment Classification
+A model trained on English Hotel Reviews from Switzerland. The base model is the [bert-base-uncased](https://huggingface.co/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
+![Confusion Matrix](bert-base-uncased_English_classification.jpg)