A review on Natural Language Processing Models for COVID-19 research

Karl Hall; Victor Chang; Chrisina Jayne

doi:10.1016/j.health.2022.100078

A review on Natural Language Processing Models for COVID-19 research

Healthc Anal (N Y). 2022 Nov:2:100078. doi: 10.1016/j.health.2022.100078. Epub 2022 Jul 19.

Authors

Karl Hall¹, Victor Chang², Chrisina Jayne¹

Affiliations

¹ SCEDT, Teesside University, UK.
² Operations Information Management, ABS, Aston University, UK.

Abstract

This survey paper reviews Natural Language Processing Models and their use in COVID-19 research in two main areas. Firstly, a range of transformer-based biomedical pretrained language models are evaluated using the BLURB benchmark. Secondly, models used in sentiment analysis surrounding COVID-19 vaccination are evaluated. We filtered literature curated from various repositories such as PubMed and Scopus and reviewed 27 papers. When evaluated using the BLURB benchmark, the novel T-BPLM BioLinkBERT gives groundbreaking results by incorporating document link knowledge and hyperlinking into its pretraining. Sentiment analysis of COVID-19 vaccination through various Twitter API tools has shown the public's sentiment towards vaccination to be mostly positive. Finally, we outline some limitations and potential solutions to drive the research community to improve the models used for NLP tasks.

Keywords: COVID-19; Machine learning; Natural Language Processing; Sentiment analysis; Transformer models.

Publication types

Review