Skip to content

cleopatra-itn/TIB_VA_MediaEval_FakeNews

Repository files navigation

Code for FakeNews MediaEval 2020 Task

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}
}