This paper presents the Multilingual COVID-19 Analysis Method (CMTA) for detecting and observing the spread of misinformation about this disease within texts. CMTA proposes a data science (DS) pipeline that applies machine learning models for processing, classifying (Dense-CNN) and analyzing (MBERT) multilingual (micro)-texts. DS pipeline data preparation tasks extract features from multilingual textual data and categorize it into specific information classes (i.e., ‘false’, ‘partly false’, ‘misleading’). The CMTA pipeline was experimented with multilingual micro-texts (tweets), showing misinformation spread across different languages. We performed a comparative analysis of CMTA with eight monolingual models used for detecting misinformation. The comparison shows that CMTA has surpassed various monolingual models and suggests that it can be used as a general method for detecting misinformation in multilingual micro-texts.
CITATION STYLE
Pranesh, R. R., Farokhnejad, M., Shekhar, A., & Vargas-Solar, G. (2021). Looking for COVID-19 Misinformation in Multilingual Social Media Texts. In Communications in Computer and Information Science (Vol. 1450 CCIS, pp. 72–81). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-85082-1_7
Mendeley helps you to discover research relevant for your work.