mlsanityData to 7 Oct 2026

Model Generalization on COVID-19 Fake News Detection

arXiv 2101.03841 ↗First posted 11 Jan 2021cs.CL cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Amid the pandemic COVID-19, the world is facing unprecedented infodemic with the proliferation of both fake and real information. Considering the problematic consequences that the COVID-19 fake-news have brought, the scientific community has put effort to tackle it. To contribute to this fight against the infodemic, we aim to achieve a robust model for the COVID-19 fake-news detection task proposed at CONSTRAINT 2021 (FakeNews-19) by taking two separate approaches: 1) fine-tuning transformers based language models with robust loss functions and 2) removing harmful training instances through influence calculation. We further evaluate the robustness of our models by evaluating on different COVID-19 misinformation test set (Tweets-19) to understand model generalization ability. With the first approach, we achieve 98.13% for weighted F1 score (W-F1) for the shared task, whereas 38.18% W-F1 on the Tweets-19 highest. On the contrary, by performing influence data cleansing, our model with 99% cleansing percentage can achieve 54.33% W-F1 score on Tweets-19 with a trade-off. By evaluating our models on two COVID-19 fake-news test sets, we suggest the importance of model generalization ability in this task to step forward to tackle the COVID-19 fake-news problem in online social media platforms.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 11 Jan 2021.

Builds on

30 of 44 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  6. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  7. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  8. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  9. 2020CORD-19: The COVID-19 Open Research Datasetcited by 179
  10. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  11. 2020CrossNER: Evaluating Cross-Domain Named Entity Recognitioncited by 102
  12. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 87
18 more
  1. 2020Fighting an Infodemic: COVID-19 Fake News Datasetcited by 82
  2. 2019Data Cleansing for Models Trained with SGDcited by 67
  3. 2020The COVID-19 Social Media Infodemiccited by 64
  4. 2020Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Armscited by 41
  5. 2020Part-dependent Label Noise: Towards Instance-dependent Label Noisecited by 40
  6. 2016Does Distributionally Robust Supervised Learning Give Robust Classifiers?cited by 38
  7. 2020The Adapter-Bot: All-In-One Controllable Conversational Modelcited by 38
  8. 2020An Exploratory Study of COVID-19 Misinformation on Twittercited by 33
  9. 2020Learning Fast Adaptation on Cross-Accented Speech Recognitioncited by 28
  10. 2020Meta-Transfer Learning for Code-Switched Speech Recognitioncited by 22
  11. 2020Zero-Resource Cross-Domain Named Entity Recognitioncited by 18
  12. 2020Misinformation Has High Perplexitycited by 15
  13. 2020A first look at COVID-19 information and misinformation sharing on Twittercited by 13
  14. 2020No Rumours Please! A Multi-Indic-Lingual Approach for COVID Fake-Tweet Detectioncited by 13
  15. 2020Efficient Estimation of Influence of a Training Instancecited by 11
  16. 2018Anatomy of an online misinformation networkcited by 8
  17. 2020Critical Impact of Social Networks Infodemic on Defeating Coronavirus COVID-19 Pandemic: Twitter-Based Study and Research Directionscited by 6
  18. 2020CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Managementcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 5; 2023: 1.

11 papers.

  1. 2022Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfercited by 19
  2. 2022A Holistic Framework for Analyzing the COVID-19 Vaccine Debatecited by 18
  3. 2021Sentiment Analysis and Topic Modeling for COVID-19 Vaccine Discussionscited by 7
  4. 2021A Heuristic-driven Uncertainty based Ensemble Framework for Fake News Detection in Tweets and News Articlescited by 5
  5. 2021Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximationcited by 5
  6. 2023IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languagescited by 5
  7. 2021Dynamically Addressing Unseen Rumor via Continual Learningcited by 3
  8. 2022Towards Answering Open-ended Ethical Quandary Questionscited by 3
  9. 2022Evaluating Generalizability of Fine-Tuned Models for Fake News Detectioncited by 3
  10. 2021Sentiment Analysis of Users' Reviews on COVID-19 Contact Tracing Apps with a Benchmark Datasetcited by 2
  11. 2022A Comparative Study on COVID-19 Fake News Detection Using Different Transformer Based Modelscited by 2