Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,38 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: eng
|
| 3 |
+
tags:
|
| 4 |
+
- bert
|
| 5 |
license: apache-2.0
|
| 6 |
+
|
| 7 |
+
widget:
|
| 8 |
+
- text: "The hotel is very nicely located"
|
| 9 |
+
example_title: "Example 1"
|
| 10 |
+
- text: "The reception staff were extremely helpful and very welcoming"
|
| 11 |
+
example_title: "Example 2"
|
| 12 |
+
- text: "There is no balcony in the rooms on the mountain side"
|
| 13 |
+
example_title: "Example 3"
|
| 14 |
+
- text: "A bit pricey"
|
| 15 |
+
example_title: "Example 4"
|
| 16 |
---
|
| 17 |
+
|
| 18 |
+
# German Hotel Review Sentiment Classification
|
| 19 |
+
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.
|
| 20 |
+
|
| 21 |
+
# Model Performance
|
| 22 |
+
|
| 23 |
+
| Classes | Precision | Recall | F1 Score |
|
| 24 |
+
| :--- | :---: | :---: |:---: |
|
| 25 |
+
| Room | 77.78% | 77.78% | 77.78% |
|
| 26 |
+
| Location | 95.45% | 95.45% | 95.45% |
|
| 27 |
+
| Staff | 75.00% | 93.75% | 83.33% |
|
| 28 |
+
| Unknown | 71.43% | 50.00% | 58.82% |
|
| 29 |
+
| HotelOrganisation | 27.27% | 30.00% | 28.57% |
|
| 30 |
+
| Food | 87.50% | 87.50% | 87.50% |
|
| 31 |
+
| ReasonForStay | 63.64% | 58.33% | 60.87%|
|
| 32 |
+
| GeneralUtility | 66.67% | 50.00% | 66.67% |
|
| 33 |
+
| Accuracy | | | 74.00% |
|
| 34 |
+
| Macro Average | 70.59%| 67.85% | 68.68% |
|
| 35 |
+
| Weighted Average | 74.17% | 74.00% | 73.66% |
|
| 36 |
+
|
| 37 |
+
## Confusion Matrix
|
| 38 |
+
|