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

Karl Hall, Victor Chang, Chrisina Jayne

Research output: Contribution to journal › Article › peer-review

83 Downloads (Pure)

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.

Original language	English
Article number	100078
Number of pages	11
Journal	Healthcare Analytics
Volume	2
Early online date	19 Jul 2022
DOIs	https://doi.org/10.1016/j.health.2022.100078
Publication status	Published - 1 Nov 2022

Access to Document

10.1016/j.health.2022.100078Licence: CC BY-NC-ND

Full textFinal published version, 1.14 MBLicence: CC BY-NC-ND

https://linkinghub.elsevier.com/retrieve/pii/S2772442522000326Licence: CC BY-NC-ND

Cite this

@article{b3b4cfe9c3774192acb51359d6501c51,

title = "A review on Natural Language Processing Models for COVID-19 research",

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{\textquoteright}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.",

author = "Karl Hall and Victor Chang and Chrisina Jayne",

year = "2022",

month = nov,

day = "1",

doi = "10.1016/j.health.2022.100078",

language = "English",

volume = "2",

journal = "Healthcare Analytics",

issn = "2772-4425",

publisher = "Elsevier",

}

TY - JOUR

T1 - A review on Natural Language Processing Models for COVID-19 research

AU - Hall, Karl

AU - Chang, Victor

AU - Jayne, Chrisina

PY - 2022/11/1

Y1 - 2022/11/1

N2 - 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.

AB - 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.

U2 - 10.1016/j.health.2022.100078

DO - 10.1016/j.health.2022.100078

M3 - Article

SN - 2772-4425

VL - 2

JO - Healthcare Analytics

JF - Healthcare Analytics

M1 - 100078

ER -

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

Abstract

Access to Document

Fingerprint

Cite this