Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep Learning

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6000–6017 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 6000 Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep Learning Yuanzhi Chen University of Nebraska-Lincoln NE 68588, USA yuanzhi@huskers.unl.edu Mohammad Rashedul Hasan University of Nebraska-Lincoln NE 68588, USA hasan@unl.edu Abstract Irrespective of the success of the deep learning- based mixed-domain transfer learning ap- proach for solving various Natural Language Processing tasks, it does not lend a general- izable solution for detecting misinformation from COVID-19 social media data. Due to the inherent complexity of this type of data, caused by its dynamic (context evolves rapidly), nuanced (misinformation types are often ambiguous), and diverse (skewed, fine- grained, and overlapping categories) nature, it is imperative for an effective model to capture both the local and global context of the target domain. By conducting a systematic investiga- tion, we show that: (i) the deep Transformer- based pre-trained models, utilized via the mixed-domain transfer learning, are only good at capturing the local context, thus exhibits poor generalization, and (ii) a combination of shallow network-based domain-specific mod- els and convolutional neural networks can effi- ciently extract local as well as global context directly from the target data in a hierarchical fashion, enabling it to offer a more generaliz- able solution. 1 Introduction Since the start of the Coronavirus or COVID-19 pandemic, online social media (e.g., Twitter) has become a conduit for rapid propagation of misin- formation (Johnson et al., 2020). Although misin- formation is considered to be created without the intention of causing harm (Lazer et al., 2018), it can wreak havoc on society (Ciampaglia, 2018; Neuman, 2020; Hamilton, 2020) and disrupt demo- cratic institutions (Ciampaglia et al., 2018). Mis- information in general, and COVID-19 misinfor- mation in particular, has become a grave concern for the policymakers due to its fast propagation via online social media. A recent study shows that the majority of the COVID-19 social media data is rife with misinformation (Brennen et al., 2020). The first step towards preventing misinformation is to detect misinformation in a timely fashion. Building automated systems for misinformation detection from social media data is a Natural Lan- guage Processing (NLP) task. Various deep learn- ing models have been successfully employed for this type of NLP task of text classification (Kim, 2014; Conneau et al., 2017; Wang et al., 2017; Tai et al., 2015; Zhou et al., 2016). These models learn language representations from a domain, which are then used as numeric features in supervised classi- fication. Due to the prohibitive cost of acquiring labeled data on COVID-19 misinformation, train- ing deep learning models directly using the target data is not a suitable approach. Background. An alternative approach for detect- ing COVID-19 misinformation from small labeled data is transfer learning (Hossain et al., 2020). The dominant paradigm of transfer learning em- ploys a mixed-domain strategy in which repre- sentations learned from a general domain (source data) by using domain-agnostic models are trans- ferred into a specific domain …

Content truncated to 500 words