Analyzing the research trends of COVID-19 using topic modeling approach

Abstract

Purpose The COVID-19 pandemic has impacted 222 countries across the globe, with millions of people losing their lives. The threat from the virus may be assessed from the fact that most countries across the world have been forced to order partial or complete shutdown of their economies for a period of time to contain the spread of the virus. The fallout of this action manifested in loss of livelihood, migration of the labor force and severe impact on mental health due to the long duration of confinement to homes or residences. Design/methodology/approach The current study identifies the focus areas of the research conducted on the COVID-19 pandemic. Abstracts of papers on the subject were collated from the SCOPUS database for the period December 2019 to June 2020. The collected sample data (after preprocessing) was analyzed using Topic Modeling with Latent Dirichlet Allocation. Findings Based on the research papers published within the mentioned timeframe, the study identifies the 10 most prominent topics that formed the area of interest for the COVID-19 pandemic research. Originality/value While similar studies exist, no other work has used topic modeling to comprehensively analyze the COVID-19 literature by considering diverse fields and domains.

Leveraging Topic Modelling to Analyze Biomedical Research Trends from the PubMed Database Using LDA Method

“…One model often used in topic modelling is Latent Dirichlet Allocation (LDA). The Latent Dirichlet Allocation (LDA) model is a probability model of textual data which can explain the correlation between words and semantic themes hidden in the document [20]. The parameter estimation used in the model is the Bayesian method.…”

Guest editorial: Modelling the business and societal decisions under the impact of COVID-19

“…The interrelationships among factors that influence the organizational dynamics to be accounted while starting up new ventures. Practitioners can use this model of Trivedi et al (2022) to further test, validate and prioritize these factors under the impact of pandemic to build concrete roadmap. The practitioners may derive helpful policies from the study of Kumar et al (2022) by designing more resilient and sustainable food supply chains.…”

“…It also helps in setting the preferences among employment alternatives to tech-economical feasibility of stakeholders. Eighth: As the state-of-art base of existing literature lacks the information about research to be conducted upon, Trivedi et al (2022) analysed sources using topic mining approach to identify the same. Though this study contributes very little to the literature, it highlights research issues that need to be addressed in contemporary pandemic time.…”

“…If yes, can we test and validate different business scenarios through simulation modelling before its actual implementation? The authorwise listing of papers cited hereafter is as follows: first: Thakkar et al (2022); second: Toumi et al (2022); third: Bhide and Akarte (2022); fourth: Wang et al (2022); fifth: Singh and Sharma (2022); sixth: Sreenivasan and Suresh (2022); seventh: Vimal et al (2022); eighth: Trivedi et al (2022); and ninth: Kumar et al (2022).…”

Latent Dirichlet Allocation-Based Topic Mining Analysis of Educational Scientific Research Projects Based on 2360 NSF Education Projects

“…LDA, based on the PLSA algorithm and originally proposed by Blei, is an unsupervised machine learning technique for identifying potential topic word information in document sets [4]. LDA topic model has proven to be well adapted in practical applications: for example, Wenjuan Wang and Jianxia Ma [5] used NSF-funded ocean acidification-related project applications and journal papers as research data for topic mining and evolution analysis, and the study found that LDA topic modeling can well mine the main research topics of these projects; Trivedi et al [6] carried out topic modeling on the research trend of the COVID-19 pandemic, and found that LDA topic modeling can help identify heterogeneous topics related to the COVID-19 pandemic other than medical topic. Tan Chunhui et al [7] constructed a sentiment analysis framework combining Baidu's sentiment analysis and LDA topic identification and studied the emotions of social media onlookers in privacy breaches.…”