publication . Conference object . Preprint . 2021

Looking for COVID-19 misinformation in multilingual social media texts

Rr, Pranesh; Farokhnejad M; Shekhar A; Genoveva Vargas Solar;
Open Access English
  • Published: 24 Aug 2021
  • Publisher: HAL CCSD
  • Country: France
Abstract
International audience; 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 has been experimented with multilingual micro-texts (tweets), showing misinformation spread across different language...
Subjects
free text keywords: natural language processing, machine learning, misinformation, data exploration, data science, [INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB], Computer Science - Computation and Language, Computer Science - Databases
Related Organizations
Any information missing or wrong?Report an Issue