Published May 7, 2021
| Version v1
Conference paper
Open
Challenges in Automated Detection of COVID-19 Misinformation
Creators
- 1. Oak Ridge National Laboratory
- 2. Institute for Advanced Computational Science, Stony Brook University
- 3. National Geospatial-Intelligence Agency
Description
The COVID-19 pandemic has made the dangers of the spread of misinformation obvious but despite much global effort to curbing its spread, fake information about the pandemic keeps proliferating. In this paper, we address the development of automated methods for verification of claims about COVID-19 and discuss the challenges associated with this task. We focus on labeled data collection, limitations of existing models, and difficulties of applying misinformation detection models in practical applications. Our initial analysis indicates label imbalance may be a particular challenge for developing claim verification models and we discuss options for alleviating this issue.
Files
CHI_2021_Misinformation_Workshop____Misinformation_Detection_Camera_Ready.pdf
Files
(381.3 kB)
Name | Size | Download all |
---|---|---|
md5:666a44b97f4449d50c563091ee085635
|
381.3 kB | Preview Download |