README.md

metadata

language:
  - ar
license: apache-2.0
tags:
  - generated_from_trainer
base_model: google-bert/bert-base-multilingual-uncased
datasets:
  - labr
widget:
  - text: كتاب يستحق القراءة
    example_title: مثال 1
  - text: ما عجبني بنوب
    example_title: مثال 2
  - text: لم يعجبني أبدا
    example_title: مثال 3
  - text: أنصح وبشدة قراءة الكتاب خصوصا لمن لديه اهتمام في العلوم الاجتماعية
    example_title: مثال 4
  - text: ماشي حالو بعطيه 4 من 10
    example_title: مثال 5
model-index:
  - name: Arabic-Book-Review-Sentiment-Assessment
    results: []

Arabic-Book-Review-Sentiment-Assessment

This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on labr dataset. It achieves the following results on the evaluation set:

• Loss: 1.5290

Model description

The purpose of this model is to analyze Arabic review texts and predict the appropriate rating for them, based on the sentiment and content of the review. This can be particularly useful in tasks such as sentiment analysis, customer feedback analysis, or any application where understanding the sentiment conveyed in an Arabic textual review is important.

The labels associated with the ratings are LABEL_0, LABEL_1, LABEL_2, LABEL_3, and LABEL_4. These labels can be interpreted as follows:

• LABEL_0: Poor
• LABEL_1: Fair
• LABEL_2: Good
• LABEL_3: Very Good
• LABEL_4: Excellent

Intended uses & limitations

While the model performs well with formal Arabic text (Examples 1, 3, and 4), it may struggle with slang or informal language, occasionally assigning higher ratings than expected (Example 2). Additionally, the model is not capable of interpreting verbally given ratings (Example 5). Users should be aware of these limitations and provide context-appropriate input for optimal performance.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.0459	1.0	1470	1.5290
0.7622	2.0	2940	1.6278
0.8204	3.0	4410	1.5341
0.6592	4.0	5880	1.8030
0.4976	5.0	7350	1.9638

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2