Main Libraries used:
- PyTorch 1.6.0
- transformers 3.3.1
Main Files:
- Feature Extraction - extract_covidbert.py
- Model Training - train_mlp_text.py
Extract the tweet dataset in a folder named dataset as instructed on challenge github page.
The paper is available here: https://arxiv.org/pdf/2101.03529.pdf
If you find this useful, please cite:
@inproceedings{DBLP:conf/mediaeval/CheemaHE20,
author = {Gullal Singh Cheema and
Sherzod Hakimov and
Ralph Ewerth},
editor = {Steven Hicks and
Debesh Jha and
Konstantin Pogorelov and
Alba Garc{\'{\i}}a Seco de Herrera and
Dmitry Bogdanov and
Pierre{-}Etienne Martin and
Stelios Andreadis and
Minh{-}Son Dao and
Zhuoran Liu and
Jos{\'{e}} Vargas Quiros and
Benjamin Kille and
Martha A. Larson},
title = {TIB's Visual Analytics Group at MediaEval '20: Detecting Fake News
on Corona Virus and 5G Conspiracy},
booktitle = {Working Notes Proceedings of the MediaEval 2020 Workshop, Online,
14-15 December 2020},
series = {{CEUR} Workshop Proceedings},
volume = {2882},
publisher = {CEUR-WS.org},
year = {2020},
url = {http://ceur-ws.org/Vol-2882/paper56.pdf},
timestamp = {Mon, 21 Jun 2021 16:26:35 +0200},
biburl = {https://dblp.org/rec/conf/mediaeval/CheemaHE20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}