|
--- |
|
language: pt |
|
widget: |
|
- text: "hoje perdi o meu trabalho.." |
|
--- |
|
|
|
# Detection of employment status disclosures on Twitter |
|
|
|
## Model main characteristics: |
|
- class: Lost Job (1), else (0) |
|
- country: BR |
|
- language: Portuguese |
|
- architecture: BERT base |
|
|
|
## Model description |
|
This model is a version of `neuralmind/bert-base-portuguese-cased` finetuned to recognize Portuguese tweets where a user mentions that she lost her job in the past month. It was trained on Portuguese tweets from users based in Brazil. The task is framed as a binary classification problem with: |
|
- the positive class referring to tweets mentioning that a user recently lost her job (label=1) |
|
- the negative class referring to all other tweets (label=0) |
|
|
|
## Resources |
|
|
|
The dataset of Portuguese tweets on which this classifier was trained is open-sourced [here](https://github.com/manueltonneau/twitter-unemployment). |
|
Details on the performance can be found in our [ACL 2022 paper](https://arxiv.org/abs/2203.09178). |
|
|
|
## Citation |
|
|
|
If you find this model useful, please cite our paper (citation to come soon). |
