Evaluating Standard Classifiers for Detecting COVID-19 related Misinformation

Published in IEEE Workshop on Parallel and Distributed Processing for Computational Social Systems, 2020

This paper summarises the results created through participation in the task FakeNews: Corona Virus and 5G Conspiracy of the MediaEval Multimedia Evaluation Challenge 2020. The task consists of two parts intending to detect tweets and retweet cascades that emerged during the COVID-19 pandemic and causally connect the radiation of 5G networks with the virus. We applied several well-established neural networks and machine learning techniques for the first subtasks, namely, textual information classification. For the second task, the retweet cascades analysis, we rely on classifiers that work on established graph features, such as the clustering coefficient or graph diameter. Our results show a MCC-score of 0.148 or 0.162 for the NLP task and 0.02 for the structure task.

Download paper here


  author       = {Daniel Thilo Schroeder and
                  Konstantin Pogorelov and
                  Johannes Langguth},
  editor       = {Steven Hicks and
                  Debesh Jha and
                  Konstantin Pogorelov and
                  Alba Garcia Seco de Herrera and
                  Dmitry Bogdanov and
                  Pierre{-}Etienne Martin and
                  Stelios Andreadis and
                  Minh{-}Son Dao and
                  Zhuoran Liu and
                  Jose Vargas Quiros and
                  Benjamin Kille and
                  Martha A. Larson},
  title        = {Evaluating Standard Classifiers for Detecting {COVID-19} Related Misinformation},
  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          = {https://ceur-ws.org/Vol-2882/paper65.pdf},
  timestamp    = {Fri, 10 Mar 2023 16:22:12 +0100},
  biburl       = {https://dblp.org/rec/conf/mediaeval/SchroederPL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}