Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model description
|
| 2 |
+
|
| 3 |
+
This model is an Arabic language sentiment analysis pretrained model.
|
| 4 |
+
The model is built on top of the CAMelBERT_msa_sixteenth BERT-based model.
|
| 5 |
+
We used the HARD dataset of hotels review to fine tune the model.
|
| 6 |
+
The dataset original labels based on a five-star rating were modified to a 3 label data:
|
| 7 |
+
- POSITIVE: for ratings > 3 stars
|
| 8 |
+
- NEUTRAL: for a 3 star rating
|
| 9 |
+
- NEGATIVE: for ratings < 3 stars
|
| 10 |
+
|
| 11 |
+
This first prototype was trained on 3 epochs for 1 hours using colab and a TPU acceleration.
|
| 12 |
+
|
| 13 |
+
If you have questions or improvement remarks, feel free to contact me on my Linkedin profile: https://www.linkedin.com/in/yahya-ghrab/
|