---
language: ar
widget:
 - text: "للوقايه من عدم انتشار [MASK]"
---
# arabert_c19: An Arabert model pretrained on 1.5 million COVID-19 multi-dialect Arabic tweets 
**ARABERT COVID-19** is a pretrained (fine-tuned) version of the AraBERT v2 model (https://huggingface.co/aubmindlab/bert-base-arabertv02). The pretraining was done using 1.5 million multi-dialect Arabic tweets regarding the COVID-19 pandemic from the “Large Arabic Twitter Dataset on COVID-19” (https://arxiv.org/abs/2004.04315).
The model can achieve better results for the tasks that deal with multi-dialect Arabic tweets in relation to the COVID-19 pandemic. 

# Classification results for multiple fake-news detection tasks with and without using the arabert_c19:
For more details refer to the paper (link)

|                                    | \multicolumn{5}{c}{Without Fine-tuning} | \multicolumn{5}{c}{With Fine-tuning}           |
|------------------------------------|-----------------------------------------|------------------------------------------------|
|                                    | \multicolumn{3}{c}{Baseline models}     | \multicolumn{2}{c}{Pretrained Covid-19 models} | \multicolumn{3}{c}{Baseline   models} | \multicolumn{2}{c}{Pretrained Covid-19 models} |
|                                    | arabert                                 | mbert                                          | distilbert-multi                      | \textbf{arabert Cov19}                         | \textbf{mbert Cov19} | arabert | mbert  | distilbert-multi | \textbf{arabert Cov19} | \textbf{mbert Cov19} |
| \textbf{Contains hate}             | 0.8346                                  | 0.6675                                         | 0.7145                                | \textbf{0.8649}                                | 0.8492               | 0.9809  | 0.97   | 0.9736           | \textbf{0.9858}        | 0.9809               |
| \textbf{Talk about a cure}         | 0.8193                                  | 0.7406                                         | 0.7127                                | 0.9055                                         | \textbf{0.9176}      | 0.99    | 0.9854 | 0.9774           | \textbf{0.9930}        | 0.9904               |
| \textbf{Give advice}               | 0.8287                                  | 0.6865                                         | 0.6974                                | \textbf{0.9035}                                | 0.8948               | 0.9793  | 0.9664 | 0.9764           | 0.9824                 | \textbf{0.9862}      |
| \textbf{Rise moral   }             | 0.8398                                  | 0.7075                                         | 0.7049                                | \textbf{0.8903}                                | 0.8838               | 0.9618  | 0.9663 | 0.9618           | 0.97                   | \textbf{0.9712}      |
| \textbf{News or opinion }          | 0.8987                                  | 0.8332                                         | 0.8099                                | \textbf{0.9163}                                | 0.9116               | 0.9552  | 0.9409 | 0.9529           | \textbf{0.9627}        | 0.9594               |
| \textbf{Dialect}                   | 0.7533                                  | 0.558                                          | 0.5433                                | \textbf{0.8230}                                | 0.7682               | 0.9266  | 0.9137 | 0.9102           | 0.9281                 | \textbf{0.9317}      |
| \textbf{Blame and negative speech} | 0.7426                                  | 0.597                                          | 0.6221                                | \textbf{0.7997}                                | 0.7794               | 0.9607  | 0.9476 | 0.9587           | \textbf{0.9653}        | 0.9633               |
| \textbf{Factual}                   | 0.9217                                  | 0.8427                                         | 0.8383                                | 0.9575                                         | \textbf{0.9608}      | 0.9958  | 0.9917 | 0.9925           | 0.995                  | \textbf{0.9967}      |
| \textbf{Worth fact-checking}       | 0.7731                                  | 0.5298                                         | 0.5413                                | 0.8265                                         | \textbf{0.8383}      | 0.9885  | 0.9824 | 0.9763           | \textbf{0.9907}        | 0.9891               |
| \textbf{Contains fake information} | 0.6415                                  | 0.5428                                         | 0.4743                                | \textbf{0.7739}                                | 0.7228               | 0.9417  | 0.9353 | 0.9288           | \textbf{0.9578}        | 0.9491               |



# Preprocessing

```python
from arabert.preprocess import ArabertPreprocessor
model_name="moha/arabert_c19"
arabert_prep = ArabertPreprocessor(model_name=model_name)
text = "للوقايه من عدم انتشار كورونا عليك اولا غسل اليدين بالماء والصابون وتكون عملية الغسل دقيقه تشمل راحة اليد الأصابع التركيز على الإبهام"
arabert_prep.preprocess(text)
```


# Contacts
**Hadj Ameur**: [Github](https://github.com/MohamedHadjAmeur) | <mohamedhadjameur@gmail.com> | <mhadjameur@cerist.dz>