Skip to content
conftrace_
2020 ACL ACL 2020

NLP-based Feature Extraction for the Detection of COVID-19 Misinformation Videos on YouTube

Abstract

AbstractWe present a simple NLP methodology for detecting COVID-19 misinformation videos on YouTube by leveraging user comments. We use transfer learning pre-trained models to generate a multi-label classifier that can categorize conspiratorial content. We use the percentage of misinformation comments on each video as a new feature for video classification.

🐣 Hot Topic Early Bird - misinformation detection

Authors

Juan Carlos Medina Serrano, Orestis Papakyriakopoulos, Simon Hegelich

Topics

Machine Learning > Core Methods > Classification Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Transfer Learning Artificial Intelligence > Core AI > Natural Language Processing Machine Learning > Application Areas > Text Classification

Keywords

transfer learning natural language processing video classification multi-label classification misinformation detection
Download PDF

More from ACL 2020

All ACL 2020 papers →
Cross-language sentiment analysis of European Twitter messages during the COVID-19 pandemic
Cross-lingual Transfer Learning for COVID-19 Outbreak Alignment
COVID-19 and Arabic Twitter: How can Arab World Governments and Public Health Organizations Learn from Social Media?
COVID-QA: A Question Answering Dataset for COVID-19
Extending ImageNet to Arabic using Arabic WordNet
Toward General Scene Graph: Integration of Visual Semantic Knowledge with Entity Synset Alignment