---
language: en        # <-- my language
widget:
 - text: "Just lost my job..."
---

# Detection of employment status disclosures on Twitter 

## Model main characteristics:
- class: Lost Job (1), else (0)
- country: US 
- language: English
- architecture: BERT base

## Model description 
This model is a version of `DeepPavlov/bert-base-cased-conversational` finetuned to recognize English tweets where a user mentions that she lost her job in the past month. It was trained on English tweets from US-based users. 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 English 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).