Edit model card

Fine-tuned RoBERTa model for detecting the level of depression as not depression, moderate or severe, based on social media posts in English.

Model was part of the winning solution for the Shared Task on Detecting Signs of Depression from Social Media Text at LT-EDI-ACL2022.

More information can be found in the following paper: OPI@LT-EDI-ACL2022: Detecting Signs of Depression from Social Media Text using RoBERTa Pre-trained Language Models.

If you use this model, please cite:

@inproceedings{poswiata-perelkiewicz-2022-opi,
    title = "{OPI}@{LT}-{EDI}-{ACL}2022: Detecting Signs of Depression from Social Media Text using {R}o{BERT}a Pre-trained Language Models",
    author = "Po{\'s}wiata, Rafa{\l} and Pere{\l}kiewicz, Micha{\l}",
    booktitle = "Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.ltedi-1.40",
    doi = "10.18653/v1/2022.ltedi-1.40",
    pages = "276--282",
}
Downloads last month
101
Safetensors
Model size
355M params
Tensor type
I64
·
F32
·
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Finetuned from