Scientific Landscape of Publications in Natural Language Processing in the ASEAN Region on COVID-19: A Bibliometric Approach

This study presents the quantitative and qualitative analyses of NLP scientific literature during the COVID-19 pandemic in the ASEAN region that used machine and/or deep learning approaches. From the 55 Scopus-indexed documents, 34 were manually identified and included in the study. The analyses reveal that 61.8 percent of these are journal articles and 38.2 percent are conference papers. Research productivity leaders in the ASEAN are Singapore for citation density; Indonesia for volume of work; and Malaysia for network strength. Thailand must fortify its link strength, but it poses as a research powerhouse with its robust number of citations. There is a trend in collaborative work with non-ASEAN countries, specifically with China, Saudi Arabia, Japan and the United States, and both local and international research funding sponsorships help increase research outputs. Prevailing themes are COVID-19 pandemic, social media, and sentiments on social media pertaining to the pandemic. More research funding sponsorships will close the research productivity gap among ASEAN countries. Tapping other sources of data, verifying social media perceptions using other sources of sentiments, and using Application Interface (API) will further enrich research on the use of machine learning (ML) and deep learning (DL) methodologies in the NLP research in the ASEAN during the COVID-19 pandemic.