Downloads · 30 days
21
1% of all-time downloads
Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD
Yah216/Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD
Sentiment_Analysis_CAMelBERT_msa_sixteenth_HARD is a text classification model from Yah216. Use it when you need a label for a piece of text. It is set up for transformers.
This model is an Arabic language sentiment analysis pretrained model. The model is built on top of the CAMelBERTmsasixteenth BERT-based model. We used the HARD dataset of hotels review to fine tune the model. The data…
All-time downloads
3.5K
Public
Repo size
437 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.h5437 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Nov 20, 2021
- SHA
- 0a8b808a
Try a prompt
Model card
From the Hugging Face model README
Model description
This model is an Arabic language sentiment analysis pretrained model. The model is built on top of the CAMelBERT_msa_sixteenth BERT-based model. We used the HARD dataset of hotels review to fine tune the model. The dataset original labels based on a five-star rating were modified to a 3 label data:
- POSITIVE: for ratings > 3 stars
- NEUTRAL: for a 3 star rating
- NEGATIVE: for ratings < 3 stars
This first prototype was trained on 3 epochs for 1 hours using Colab and a TPU acceleration.
Examples
Here are some examples in Arabic to test :
- Excellent -> ممتاز(Happy)
- I'am sad -> أنا حزين (Sad)
- Nothing -> لا شيء (Neutral)
Contact
If you have questions or improvement remarks, feel free to contact me on my LinkedIn profile: https://www.linkedin.com/in/yahya-ghrab/
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Languages
- ar
- Created
- Mar 2, 2022
- Updated
- Nov 20, 2021