ABSTRACT
False claims or Fake News related to the health care or medicine field on Social Media have garnered increasing amounts of interest, especially in the aftermath of the COVID-19 pandemic. False claims about the pan-demic which spread on social media have contributed to vaccine hesitancy and lack of trust in the advise of medical professionals. If not detected and disproved early, such claims can complicate future pandemic responses. We focus on false claims in the field of Neurodevelopmental Disorders (NDDs), which is an umbrella term for a group of disorders that includes Autism, ADHD, Cerebral Palsy, etc. In this paper we present our approach to automated systems for fact-checking medical articles related to NDDs. We also present an annotated dataset of 116 web pages which we use to test our model and present our results. © 2022 IEEE.
ABSTRACT
Most major events are often accompanied by misinformation on online Social Networking platforms. Due to its nature, the COVID-19 pandemic was bound to lead to an explosion of information online, much of it false or misleading. This information explosion, termed "infodemic"by the World Health Organization (WHO), has revealed the need for automatic fake news detection to help with the exponentially growing flow of unverified information. The objective of this study is to explore combinations of different supervised classification models trained on different general and domain-specific embeddings, and compare the effects of the iterations on the results. We also analyze the results to determine whether the differences in weighted F1-score performance metrics are statistically significant. Ultimately, we demonstrate that concatenation of general and context-specific embeddings improves performance. Our research shows promise for health misinformation detection and formulation of effective public health responses. © 2021 IEEE.