Fake News Detection in Social Media using Graph Neural Networks and NLP Techniques: A COVID-19 Use-case

TL;DR

This paper explores fake news detection related to COVID-19 and 5G conspiracy theories on Twitter, utilizing NLP techniques like BERT and Bag of Words, along with Graph Neural Networks for structure-based analysis, achieving promising results.

Contribution

It introduces multiple NLP-based methods and GNNs for fake news detection in social media, specifically addressing COVID-19 and 5G conspiracy theories, with new classification approaches and performance benchmarks.

Findings

BERT-based methods achieved up to 69.3% F1-score in binary classification.

GNNs achieved an average ROC of 95% in structure-based detection.

Proposed solutions outperform baseline models on the dataset.

Abstract

The paper presents our solutions for the MediaEval 2020 task namely FakeNews: Corona Virus and 5G Conspiracy Multimedia Twitter-Data-Based Analysis. The task aims to analyze tweets related to COVID-19 and 5G conspiracy theories to detect misinformation spreaders. The task is composed of two sub-tasks namely (i) text-based, and (ii) structure-based fake news detection. For the first task, we propose six different solutions relying on Bag of Words (BoW) and BERT embedding. Three of the methods aim at binary classification task by differentiating in 5G conspiracy and the rest of the COVID-19 related tweets while the rest of them treat the task as ternary classification problem. In the ternary classification task, our BoW and BERT based methods obtained an F1-score of .606% and .566% on the development set, respectively. On the binary classification, the BoW and BERT based solutions obtained an average F1-score of .666% and .693%, respectively. On the other hand, for structure-based fake news detection, we rely on Graph Neural Networks (GNNs) achieving an average ROC of .95% on the development set.