ABSTRACT
COVID-19 has caused havoc globally due to its transmission pace among the inhabitants and prolific rise in the number of people contracting the disease worldwide. As a result, the number of people seeking information about the epidemic via Internet media has increased. The impact of the hysteria that has prevailed makes people believe and share everything related to illness without questioning its truthfulness. As a result, it has amplified the misinformation spread on social media networks about the disease. Today, there is an immediate need to restrict disseminating false news, even more than ever before. This paper presents an early fusion-based method for combining key features extracted from context-based embeddings such as BERT, XLNet, and ELMo to enhance context and semantic information collection from social media posts and achieve higher accuracy for false news identification. From the observation, we found that the proposed early fusion-based method outperforms models that work on single embeddings. We also conducted detailed studies using several machine learning and deep learning models to classify misinformation on social media platforms relevant to COVID-19. To facilitate our work, we have utilized the dataset of "CONSTRAINT shared task 2021". Our research has shown that language and ensemble models are well adapted to this role, with a 97% accuracy.
ABSTRACT
Significant public health events of the 21st century include epidemic prone diseases such as severe acute respiratory syndrome (SARS), Middle East respiratory syndrome (MERS), influenza A (H1N1), Ebola virus disease, and coronavirus (SARS-COV-2). Preparedness as well as risk mitigation strategies play an integral role for the success of responses to such health emergencies. An extraordinary cluster of cases of respiratory disease of unknown cause triggered a series of events that constituted a public health risk across the globe through international spread from China and was declared a Public Health Emergency of International Concern (PHEIC) on 30 January, 2020 by the World Health Organization (WHO). To monitor implementation of activities in order to contain the local transmission of COVID-2019 in India, a control room was established at the National Centre for Disease Control (NCDC), New Delhi on 23rd January, 2020 under the Integrated Disease Surveillance Project (IDSP). The main objectives of the control room were to alleviate the concerns and address queries of passengers arriving from the affected countries and also to provide the general public information regarding the measures to be taken as well as the contact details of the respected district health authorities for further necessary action. A total of 183 hunting lines were established at the NCDC, Noida, TB Centre, and the National Health Authority (NHA) Hyderabad and Bengaluru by March 2020. A total of 79,013 calls, 1,04,779 emails, and 1,787 international calls were received w.e.f. 23 January to 30 March, 2020 at the NCDC control room. The NHA Bengaluru and Hyderabad Control room received 3,52,176 calls w.e.f. 15 March to 30 March and TB Noida control room received 55,018 calls w.e.f. 16 March to 30 March, 2020. This prompt action of the center to set up a control room at the NCDC gave the states enough grace period to train their staff and start their individual help lines for addressing people's queries and allay fears.