Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
datasets:
|
| 4 |
- abullard1/steam-reviews-constructiveness-binary-label-annotations-1.5k
|
| 5 |
language:
|
|
@@ -60,7 +61,7 @@ model-index:
|
|
| 60 |
</div>
|
| 61 |
<hr>
|
| 62 |
|
| 63 |
-
## Model Summary
|
| 64 |
|
| 65 |
This model is a fine-tuned version of **albert-base-v2**, designed to classify whether Steam game reviews are constructive or non-constructive. It leverages the [1.5K Steam Reviews Binary Labeled for Constructiveness dataset](https://huggingface.co/datasets/abullard1/steam-reviews-constructiveness-binary-label-annotations-1.5k), containing user-generated game reviews labeled as either:
|
| 66 |
- **1 (constructive)**
|
|
@@ -83,7 +84,7 @@ The model can be applied in any scenario where it's important to distinguish bet
|
|
| 83 |
- **Domain Specificity**: The model was trained on Steam reviews and may not generalize well outside gaming.
|
| 84 |
- **Dataset Imbalance**: The training data has an approximate 63%-37% split between non-constructive and constructive reviews.
|
| 85 |
|
| 86 |
-
## Evaluation Results
|
| 87 |
|
| 88 |
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:
|
| 89 |
|
|
@@ -96,7 +97,7 @@ These results indicate that the model performs reasonably well at identifying th
|
|
| 96 |
|
| 97 |
<hr>
|
| 98 |
|
| 99 |
-
## How to Use
|
| 100 |
|
| 101 |
### Via the Huggingface Space
|
| 102 |
Explore and test the model interactively on its [Hugging Face Space](https://huggingface.co/spaces/abullard1/steam-review-constructiveness-classifier).
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
license_link: https://mit-license.org/
|
| 4 |
datasets:
|
| 5 |
- abullard1/steam-reviews-constructiveness-binary-label-annotations-1.5k
|
| 6 |
language:
|
|
|
|
| 61 |
</div>
|
| 62 |
<hr>
|
| 63 |
|
| 64 |
+
## <u>Model Summary</u>
|
| 65 |
|
| 66 |
This model is a fine-tuned version of **albert-base-v2**, designed to classify whether Steam game reviews are constructive or non-constructive. It leverages the [1.5K Steam Reviews Binary Labeled for Constructiveness dataset](https://huggingface.co/datasets/abullard1/steam-reviews-constructiveness-binary-label-annotations-1.5k), containing user-generated game reviews labeled as either:
|
| 67 |
- **1 (constructive)**
|
|
|
|
| 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:
|
| 90 |
|
|
|
|
| 97 |
|
| 98 |
<hr>
|
| 99 |
|
| 100 |
+
## <u>How to Use</u>
|
| 101 |
|
| 102 |
### Via the Huggingface Space
|
| 103 |
Explore and test the model interactively on its [Hugging Face Space](https://huggingface.co/spaces/abullard1/steam-review-constructiveness-classifier).
|