Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection. Wahle, J. P., Ashok, N., Ruas, T., Meuschke, N., Ghosal, T., & Gipp, B. In Information for a Better World: Shaping the Global Future, volume 13192, pages 381–392. Springer International Publishing.
Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection [link]Paper  doi  abstract   bibtex   
A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for flagging online misinformation related to COVID-19. However, these methods predominantly target specific content types (e.g., news) or platforms (e.g., Twitter). The methods’ capabilities to generalize were largely unclear so far. We evaluate fifteen Transformer-based models on five COVID-19 misinformation datasets that include social media posts, news articles, and scientific papers to fill this gap. We show tokenizers and models tailored to COVID-19 data do not provide a significant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems.
@incollection{WahleARM22b,
  title = {Testing the {{Generalization}} of {{Neural Language Models}} for {{COVID-19 Misinformation Detection}}},
  booktitle = {Information for a {{Better World}}: {{Shaping}} the {{Global Future}}},
  author = {Wahle, Jan Philip and Ashok, Nischal and Ruas, Terry and Meuschke, Norman and Ghosal, Tirthankar and Gipp, Bela},
  editor = {Smits, Malte},
  date = {2022},
  volume = {13192},
  pages = {381--392},
  publisher = {{Springer International Publishing}},
  location = {{Cham}},
  doi = {10.1007/978-3-030-96957-8_33},
  url = {https://link.springer.com/10.1007/978-3-030-96957-8_33},
  urldate = {2022-11-11},
  abstract = {A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for flagging online misinformation related to COVID-19. However, these methods predominantly target specific content types (e.g., news) or platforms (e.g., Twitter). The methods’ capabilities to generalize were largely unclear so far. We evaluate fifteen Transformer-based models on five COVID-19 misinformation datasets that include social media posts, news articles, and scientific papers to fill this gap. We show tokenizers and models tailored to COVID-19 data do not provide a significant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems.},
  isbn = {978-3-030-96956-1 978-3-030-96957-8},
  langid = {english},
  file = {C:\Users\ruast\Zotero\storage\VJGM7QZF\WahleARM22b--tr--testing_the_generalization_of_neural_language_models_for_covid-19_misinformation.pdf}
}

Downloads: 0