Towards Checking Veracity of Medical Claims

• Author / Creator

  Dhankar, Abhishek

• Medical Fake News is a pervasive part of the information that people consume on the internet. It may lead people to take actions which may put the lives of their family and community in danger - such actions include vaccine hesitancy, administering unverified and harmful treatments, etc. First step towards countering such fake news is to detect it. In this report we explore various approaches to automatically detect and determine the veracity of textual claims, especially but not limited to medical claims, found online in social media posts and articles. In this report we present (1) An automated veracity checker for online articles pertaining to NeuroDevelopmental Disorders (NDDs) (2) Our work on detection of fake news in social media posts related to COVID-19 (3) Our approach to the shared task of Multi-Modal Fake News detection at the De-FACTIFY Workshop collocated with AAAI'22, where we secured the 4th position on the leaderboard.

• Subjects / Keywords

  • automated fact-checking
  • Neurodevelopmental Disorders
  • Fake News
  • Transfer Learning
  • Multi-Modal Fact-Checking
  • Natural Language Processing
  • Machine Learning
  • Artificial Intelligence
  • Misinformation

• Graduation date

  Fall 2022

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-kfbb-4p50

• License

  This thesis is made available by the University of Alberta Library with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.