COVID-19 Misinformation on Twitter: Multilingual Analysis

Raj Ratn Pranesh, Mehrdad Farokhenajd, Ambesh Shekhar, Genoveva Vargas-Solar

Abstract: In the current scenario of the coronavirus disease pandemic (COVID-19), the Internet has become an important source of health information for users worldwide. During pandemic situations, myths, sensationalism, rumours and misinformation, generated intentionally or unintentionally, spread rapidly through social networks. Twitter is one of these popular social networks people use to share COVID-19related news, information, and thoughts that reflect their perception and opinion about the pandemic. Analysis of tweets for identifying misinformation can generate valuable insight to evaluate the quality and readability of online information about the COVID-19. This paper presents a multilingual COVID-19 related tweet analysis method, CMTA, that usesBERT, a deep learning model for multilingual tweet misinformation detection and classification.CMTA extracts features from multilingual textual data, which is then categorized into specific information classes. Classification is done by a Dense-CNN model trained on tweets manually annotated into information classes (i.e., ’false’, ’partly false’, ’misleading’). The paper assesses CMTA experimenting an analysis of multilingual tweets from February to June, showing the distribution type of information spread across different languages.