Update README.md
Browse files
README.md
CHANGED
|
@@ -84,6 +84,8 @@ The model can be applied in any scenario where it's important to distinguish bet
|
|
| 84 |
- **Domain Specificity**: The model was trained on Steam reviews and may not generalize well outside gaming.
|
| 85 |
- **Dataset Imbalance**: The training data has an approximate 63%-37% split between non-constructive and constructive reviews.
|
| 86 |
|
|
|
|
|
|
|
| 87 |
## <u>Evaluation Results</u>
|
| 88 |
|
| 89 |
The model was trained and evaluated using an 80/10/10 Train/Dev/Test split, achieving the following performance metrics during evaluation using the test set:
|
|
|
|
| 84 |
- **Domain Specificity**: The model was trained on Steam reviews and may not generalize well outside gaming.
|
| 85 |
- **Dataset Imbalance**: The training data has an approximate 63%-37% split between non-constructive and constructive reviews.
|
| 86 |
|
| 87 |
+
<hr>
|
| 88 |
+
|
| 89 |
## <u>Evaluation Results</u>
|
| 90 |
|
| 91 |
The model was trained and evaluated using an 80/10/10 Train/Dev/Test split, achieving the following performance metrics during evaluation using the test set:
|