Tracking COVID-19 vaccine hesitancy and logistical challenges: A machine learning approach

Dutta, Shantanu; Kumar, Ashok; Dutta, Moumita; Walsh, Caolan

doi:10.1371/journal.pone.0252332

Cited by 5 publications

(6 citation statements)

References 24 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, political disagreement over vaccines could be detrimental because they were often associated with vaccine hesitancy, reduced confidence in scientific and health facts [ 71 ], and decreased policy support for immunizations [ 72 ]. Recent research suggested that as different vaccines passed phase trials and were made available to the public, the discussions over vaccine efficacy and safety sharply increased in the United States [ 73 ].…”

Section: Discussionmentioning

confidence: 99%

Characterization of Vaccine Tweets During the Early Stage of the COVID-19 Outbreak in the United States: Topic Modeling Analysis

Jiang¹,

Chu²,

Sun³

2021

JMIR Infodemiology

View full text Add to dashboard Cite

Background During the early stages of the COVID-19 pandemic, developing safe and effective coronavirus vaccines was considered critical to arresting the spread of the disease. News and social media discussions have extensively covered the issue of coronavirus vaccines, with a mixture of vaccine advocacies, concerns, and oppositions. Objective This study aimed to uncover the emerging themes in Twitter users’ perceptions and attitudes toward vaccines during the early stages of the COVID-19 outbreak. Methods This study employed topic modeling to analyze tweets related to coronavirus vaccines at the start of the COVID-19 outbreak in the United States (February 21 to March 20, 2020). We created a predefined query (eg, “COVID” AND “vaccine”) to extract the tweet text and metadata (number of followers of the Twitter account and engagement metrics based on likes, comments, and retweeting) from the Meltwater database. After preprocessing the data, we tested Latent Dirichlet Allocation models to identify topics associated with these tweets. The model specifying 20 topics provided the best overall coherence, and each topic was interpreted based on its top associated terms. Results In total, we analyzed 100,209 tweets containing keywords related to coronavirus and vaccines. The 20 topics were further collapsed based on shared similarities, thereby generating 7 major themes. Our analysis characterized 26.3% (26,234/100,209) of the tweets as News Related to Coronavirus and Vaccine Development, 25.4% (25,425/100,209) as General Discussion and Seeking of Information on Coronavirus, 12.9% (12,882/100,209) as Financial Concerns, 12.7% (12,696/100,209) as Venting Negative Emotions, 9.9% (9908/100,209) as Prayers and Calls for Positivity, 8.1% (8155/100,209) as Efficacy of Vaccine and Treatment, and 4.9% (4909/100,209) as Conspiracies about Coronavirus and Its Vaccines. Different themes demonstrated some changes over time, mostly in close association with news or events related to vaccine developments. Twitter users who discussed conspiracy theories, the efficacy of vaccines and treatments, and financial concerns had more followers than those focused on other vaccine themes. The engagement level—the extent to which a tweet being retweeted, quoted, liked, or replied by other users—was similar among different themes, but tweets venting negative emotions yielded the lowest engagement. Conclusions This study enriches our understanding of public concerns over new vaccines or vaccine development at early stages of the outbreak, bearing implications for influencing vaccine attitudes and guiding public health efforts to cope with infectious disease outbreaks in the future. This study concluded that public concerns centered on general policy issues related to coronavirus vaccines and that the discussions were considerably mixed with political views when vaccines were not made available. Only a small proportion of tweets focused on conspiracy theories, but these tweets demonstrated high engagement levels and were often contributed by Twitter users with more influence.

show abstract

Section: Discussionmentioning

confidence: 99%

Characterization of Vaccine Tweets During the Early Stage of the COVID-19 Outbreak in the United States: Topic Modeling Analysis

Jiang¹,

Chu²,

Sun³

2021

JMIR Infodemiology

View full text Add to dashboard Cite

show abstract

“…For reference, the entirety of the selected papers can be found in Table 1, and their citations are as follows: Ghanchi et al 2020a, b;Elkhouly et al 2020;Mulvey et al 2020;Sun et al 2020;Lu et al 2020;Beato-Víbora 2020;Mehra et al 2020a, b;Mehra et al 2020a, b;Walach et al 2021;Dutta et al 2021;Friedlich et al 2021;Ali et al 2020a, b;Lin 2021;Ali et al 2020a, b;Khalifa et al 2020;Gul et al 2021;Victor 2020a, b;Victor 2020a, b;Colchero et al 2021;Saha et al 2021;Ma et al 2021;Imran et al 2021;Akbar et al 2020;Ferdous et al 2021;Jiménez-Ruiz et al 2021;Savaris et al 2021;Grech 2020a, b;Zago Filho et al 2020;Atangana et al 2021;Mao et al 2021;Fioranelli et al 2020;Deokar et al 2020;Temmerman 2021;Ibrahimagić et al 2021;Saxena 2020;Grech 2020a, b;Din et al 2020;Bae et al 2020;Zeng et al 2020;Funck-Brentano et al 2020;Woodle et al 2021;…”

Section: Resultsmentioning

confidence: 99%

Biased, wrong and counterfeited evidences published during the COVID-19 pandemic, a systematic review of retracted COVID-19 papers

et al. 2022

View full text Add to dashboard Cite

In 2020 COVID-19 led to an unprecedented stream of papers being submitted to journals. Scientists and physicians all around the globe were in need for information about this new disease. In this climate, many articles were accepted after extremely fast peer-reviews to provide the scientific community with the latest discoveries and knowledge. Unfortunately, this also led to articles retraction due to authors’ misconduct or errors in methodology and/or conclusions. The aim of this study is to investigate the number and characteristics of retracted papers, and to explore the main causes that led to retraction. We conducted a systematic review on retracted articles, using PubMed as data source. Our inclusion criteria were the following: English-language retracted articles that reported original data, results, opinions or hypotheses on COVID-19 and Sars-CoV-2. Twenty-seven retracted articles were identified, mainly reporting observational studies and opinion pieces. Many articles published during the first year of the pandemic have been retracted, mainly due to the authors' scientific misconduct. Duplications, plagiarism, frauds and absence of consent, were the main reasons for retractions. In modern medicine, researchers are required to publish frequently, and, especially during situations like the COVID-19 pandemic, when articles were rapidly published, gaps in peer-reviews system and in the path to scientific publication arose.

show abstract

“…In this study, we have processed the text at multiple stages with the help of Spacy (version 2.3.5)— a free , open-source Natural Language Processing library for Python , Stanza (version 1.1.1), Gensim (version 3.8.3), and Regular Expression package (version 2020.11.13) toolkits [ 73 ]. We have briefly discussed these stages below:…”

Section: Methodsmentioning

confidence: 99%

“…Data pre-processing. In this study, we have processed the text at multiple stages with the help of Spacy (version 2.3.5)-a free, open-source Natural Language Processing library for Python, Stanza (version 1.1.1), Gensim (version 3.8.3), and Regular Expression package (version 2020.11.13) toolkits [73]. We have briefly discussed these stages below: a. Pre-processing sentences: Regex has been used to eliminate "E-mails, URLs, punctuations, new line characters, single characters, digits (i.e., numbers), and extra spaces" [22,74].…”

Section: Sample Collectionmentioning

confidence: 99%

Using 10-K text to gauge COVID-related corporate disclosure

Dutta

Kumar

Pant³

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

During the pandemic era, COVID-related disclosure has become quite critical for shareholders and other market participants to understand the uncertainties and challenges associated with a firm’s operation. However, there is no well-grounded and systematic measure to gauge the intensity of COVID-related disclosure and its plausible impact. Therefore, this study develops and validates various COVID-related disclosure measures. More specifically, using a sample of publicly listed U.S. firms and applying natural language processing (NLP) on 10-K reports, we have developed two types of COVID dictionaries (or COVID-related disclosure measurement tools): (a) overall COVID dictionary (count of all COVID-related words/phrases) and (b) contextual COVID-dictionary (count of COVID related words/phrases preceded or followed by positive, negative tones, or financial constraints words). Subsequently, we have validated both types of COVID dictionaries by investigating their association with corporate liquidity events (e.g., dividend payment, dividend change). We confirm that the overall COVID dictionary effectively predicts a firm’s liquidity event. We find similar results for contextual COVID dictionaries with a negative spin (i.e., COVID disclosures with a negative tone or an indication of financial constraints). Our results further show that better-governed firms (e.g., greater board independence, and more female directors) tend to have more COVID-related disclosures, despite the fact that more COVID-related disclosures suppress a firm’s market-based stock performance (e.g. Tobin’s Q). Our results suggest that better-governed firms prefer greater transparency, even if it may hurt their market performance in the short run.

show abstract

Tracking COVID-19 vaccine hesitancy and logistical challenges: A machine learning approach

Cited by 5 publications

References 24 publications

Characterization of Vaccine Tweets During the Early Stage of the COVID-19 Outbreak in the United States: Topic Modeling Analysis

Characterization of Vaccine Tweets During the Early Stage of the COVID-19 Outbreak in the United States: Topic Modeling Analysis

Biased, wrong and counterfeited evidences published during the COVID-19 pandemic, a systematic review of retracted COVID-19 papers

Using 10-K text to gauge COVID-related corporate disclosure

Contact Info

Product

Resources

About