Research Article
Textual analysis of Covid-19: A Review
@INPROCEEDINGS{10.4108/eai.16-4-2022.2318113, author={Omswroop Thakur and Sri Khetwat Saritha and Sweta Jain}, title={Textual analysis of Covid-19: A Review}, proceedings={Proceedings of The International Conference on Emerging Trends in Artificial Intelligence and Smart Systems, THEETAS 2022, 16-17 April 2022, Jabalpur, India}, publisher={EAI}, proceedings_a={THEETAS}, year={2022}, month={6}, keywords={nlp sentiment analysis covid-19 lstm roberta lda top2vec}, doi={10.4108/eai.16-4-2022.2318113} }- Omswroop Thakur
Sri Khetwat Saritha
Sweta Jain
Year: 2022
Textual analysis of Covid-19: A Review
THEETAS
EAI
DOI: 10.4108/eai.16-4-2022.2318113
Abstract
The evaluation of the sentiments from COVID-19 text data has received a lot of importance seeing the current situation of pandemics. This research focuses on the evaluation of sentiments of COVID-19 text data, which is effective for analyzing information in tweets where opinions are either negative, neutral, or positive. Social media platforms are conveying a variety of sentiments as well as a variety of emotions in different events of the outbreak. The intention of this paper is to review the related research in the field of textual analysis such as topic modeling, emotion detection, sentiment analysis ,text summarization of COVID-19 text data. And also, along with this, we differentiate earlier techniques of mining opinions/sentiments, such as machine learning, deep learning, and lexicon-based approaches, as well as their evaluation methodologies. After investigating and reviewing the various methods, in totality ,the BERT based model gives better performance than other approaches and BernoulliNB based model gave the least performance among the methodologies. Since, manual evaluation or judgment of the sentiments or emotions of the huge amount of textual content of COVID-19 text can be very challenging and infeasible due to the enormous outspread of the COVID-19 disease and thus, the need for comprehensive and systematic analysis of vast text data is the research motivation of the work.