ABSTRACT
Online misinformation has become a major concern in recent years, and it has been further emphasized during the COVID-19 pandemic. Social media platforms, such as Twitter, can be serious vectors of misinformation online. In order to better understand the spread of these fake-news, lies, deceptions, and rumours, we analyze the correlations between the following textual features in tweets: emotion, sentiment, political bias, stance, veracity and conspiracy theories. We train several transformer-based classifiers from multiple datasets to detect these textual features and identify potential correlations using conditional distributions of the labels. Our results show that the online discourse regarding some topics, such as COVID-19 regulations or conspiracy theories, is highly controversial and reflects the actual U.S. political landscape. © 2023 ACM.
ABSTRACT
Misinformation in online media has become a major research topic the last few years, especially during the COVID-19 pandemic. Indeed, false or misleading news about coronavirus have been characterized as an infodemic1 by the World Health Organization, because of how fast it can spread online. A considerable vector of spreading misinformation is represented by conspiracy theories. During this challenge, we tackled the problem of detecting COVID-19-related conspiracy theories in tweets. To perform this task, we used different approaches such as a combination of TFIDF and machine learning algorithms, transformer-based neural networks or Natural Language Inference. Our best model obtains a MCC score of 0.726 for the main task on the validation set and a MCC score of 0.775 on the test set making it the best performing method among the challenge competitors. Copyright 2021 for this paper by its authors.