A text-mining analysis of public perceptions and topic modeling during the COVID-19 pandemic using Twitter data (Preprint)

Sakun Boon-Itt
<span title="2020-06-30">2020</span> <i title="JMIR Publications Inc."> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/l4d2cstvknamhpnofbe3dxtlpe" style="color: black;">JMIR Public Health and Surveillance</a> </i> &nbsp;
Coronavirus disease (COVID-19) is a scientifically and medically novel disease that is not fully understood as it needs to be consistently and deeply studied. Concerning research on the COVID-19 outbreak, there is a lack of sufficient information regarding infoveillance data. This study aims to understand public awareness of COVID-19 pandemic trends and uncover meaningful themes of concern posted by Twitter users in the English language during the pandemic. Data mining on Twitter was conducted
more &raquo; ... o collect a total of 107,990 tweets related to COVID-19 between December 13 and March 9, 2020. The analysis included frequency of keywords, sentiment analysis, and topic modeling to identify and explore discussion topics over time. The natural language processing (NLP) approach and the latent Dirichlet allocation (LDA) algorithm were used to identify the most common tweet topics as well as to categorize clusters and find themes from keyword analysis. The results indicate three main aspects of public awareness and concerns regarding the COVID-19 pandemic. First, the study indicates the trend of the spread and symptoms of COVID-19, which was divided into three stages. Second, the results of the sentiment analysis and emotional tendency show that people have a negative outlook toward COVID-19. Third, topic modeling and themes relating to COVID-19 and the outbreak were divided into three categories, including (1) the COVID-19 pandemic emergency, (2) how to control COVID-19, and (3) reports on COVID-19. Sentiment analysis and topic modeling can produce useful information about the trend of the COVID-19 pandemic as well as alternative perspectives to investigate the COVID-19 crisis, which has created considerable public awareness. This finding shows that Twitter is a good communication channel for understanding both public concern and public awareness about the COVID-19 disease. These findings can help health departments to communicate information as to specific public concerns about the disease.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2196/21978">doi:10.2196/21978</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33108310">pmid:33108310</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c4m5tlvvhjdk3do4agyreyntcy">fatcat:c4m5tlvvhjdk3do4agyreyntcy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211204100645/https://publichealth.jmir.org/2020/4/e21978/pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/27/ef/27ef61a155628fe9f5558e68a12b7653768ba38a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2196/21978"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>