Sentiment, Contents, and Retweets: A Study of Two Vaccine-Related Twitter Datasets

Blankenship, Elizabeth B.; Goff, Mary Elizabeth; Yin, Jingjing; Tse, Zion Tsz Ho; Fu, King‐Wa; Liang, Hai; Saroha, Nitin; Fung, Isaac Chun-Hai

doi:10.7812/tpp/17-138

Cited by 140 publications

(97 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our findings suggest a possibility of divergent interests between countries of different levels of economic development with regard to the types of HIV/AIDS-related information being shared on Twitter. These results echo observations that social media users reacted to infectious disease outbreaks differently between different communities or countries [7,8]. However, since location data is self-reported, and country-level income data does not apply to individuals (ecological fallacy), the authors caution against over-interpretation of the results of this exploratory study.…”

Section: Discussionsupporting

confidence: 77%

“…Social media analysis revealed users' reactions to specific health promotion events [6]. Users from different countries might react to the same disease differently [7,8]. Research comparing Twitter contents of five different languages pertinent to the MERS outbreak in South Korea in 2015 found that users from different Asian countries had different concerns about the outbreak [7].…”

Section: Introductionmentioning

confidence: 99%

“…Users from different countries might react to the same disease differently [7,8]. Research comparing Twitter contents of five different languages pertinent to the MERS outbreak in South Korea in 2015 found that users from different Asian countries had different concerns about the outbreak [7]. Research comparing English tweets with Chinese Weibo posts pertinent to Ebola also identified content topics specific to Chinese internet users [8].…”

Section: Introductionmentioning

confidence: 99%

“…In the past few years, our team at Georgia Southern University has met our students' educational needs through various student projects [7,14,15,[18][19][20]. Some projects focused on specific health topics, such as sentiment, contents, and retweets of vaccine-related tweets [7]. Others focused on a specific Twitter profile, such as the CDC's Office of Advanced Molecular Detection (@CDC_AMD) [18].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Pedagogical Demonstration of Twitter Data Analysis: A Case Study of World AIDS Day, 2014

Fung

Yin

Pressley

et al. 2019

Data

Self Cite

View full text Add to dashboard Cite

As a pedagogical demonstration of Twitter data analysis, a case study of HIV/AIDS-related tweets around World AIDS Day, 2014, was presented. This study examined if Twitter users from countries with various income levels responded differently to World AIDS Day. The performance of support vector machine (SVM) models as classifiers of relevant tweets was evaluated. A manual coding of 1,826 randomly sampled HIV/AIDS-related original tweets from November 30 through December 2, 2014 was completed. Logistic regression was applied to analyze the association between the World Bank-designated income level of users’ self-reported countries and Twitter contents. To identify the optimal SVM model, 1278 (70%) of the 1826 sampled tweets were randomly selected as the training set, and 548 (30%) served as the test set. Another 180 tweets were separately sampled and coded as the held-out dataset. Compared with tweets from low-income countries, tweets from the Organization for Economic Cooperation and Development countries had 60% lower odds to mention epidemiology (adjusted odds ratio, aOR = 0.404; 95% CI: 0.166, 0.981) and three times the odds to mention compassion/support (aOR = 3.080; 95% CI: 1.179, 8.047). Tweets from lower-middle-income countries had 79% lower odds than tweets from low-income countries to mention HIV-affected sub-populations (aOR = 0.213; 95% CI: 0.068, 0.664). The optimal SVM model was able to identify relevant tweets from the held-out dataset of 180 tweets with an accuracy (F1 score) of 0.72. This study demonstrated how students can be taught to analyze Twitter data using manual coding, regression models, and SVM models.

show abstract

Section: Discussionsupporting

confidence: 77%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pedagogical Demonstration of Twitter Data Analysis: A Case Study of World AIDS Day, 2014

Fung

Yin

Pressley

et al. 2019

Data

Self Cite

View full text Add to dashboard Cite

show abstract

“… 11 Research from large datasets of vaccine-related tweets shows that anti-vaccine tweets are retweeted over 4 times more frequently than neutral tweets, while pro-vaccine tweets are retweeted one-and-a-half times more frequently. 11 Antivaccine tweets more frequently mention the risks or dangers of vaccines and distrust of scientific organizations and government. 11 For pro-vaccine tweets, the most common themes appear to be related to global vaccination efforts, scientific organizations, the efficacy of vaccines, and outbreaks that could have been prevented by vaccines.…”

Section: Introductionmentioning

confidence: 99%

Tweeting the #flushot: Beliefs, Barriers, and Threats During Different Periods of the 2018 to 2019 Flu Season

Guidry

Austin

O’Donnell

et al. 2020

J Prim Care Community Health

View full text Add to dashboard Cite

Influenza epidemics happen every year, with more than 8 million severe cases in 2017. The most effective way to prevent seasonal influenza is vaccination. In recent years, misinformation regarding vaccines abounds on social media, but the flu vaccine is relatively understudied in this area, and the current study is the first 1 to explore the content and nature of influenza information that is shared on Twitter, comparing tweets published in the early flu season with those posted in peak flu season. Using a quantitative content analysis, 1000 tweets from both parts of the flu season were analyzed for use of Health Belief Model (HBM) variables, engagement, and flu vaccine specific variables. Findings show several promising opportunities for health organizations and professionals: HBM constructs were present more frequently than in previous, related studies, and fewer vaccine-hesitant tweets appear to be present. However, the presence of high barriers to flu vaccine uptake increased significantly from early to peak season, including an increase in the mention of conspiracy theories. Flu vaccine related tweets appear to vary in misinformation level and density throughout the flu season. While this should be confirmed by further studies over multiple flu seasons, this a finding that should be considered by public health organizations when developing flu vaccine campaigns on social media.

show abstract

Social Media, Vaccines, and Partisan Division of Health Information

Hagen

Greyson

Fox

et al. 2021

Proceedings of the Association for Information Science and Tech

View full text Add to dashboard Cite

Vaccine confidence and uptake is essential to achieving herd immunity levels sufficient to end the COVID-19 pandemic; however, polarized and partisan discussion on vaccines have increased the difficulty of achieving sufficient vaccine coverage in the population. As individual's health information seeking behaviors diversify, studies suggest that social media is a major "battle ground" for shaping attitudes toward vaccines. Interdisciplinary experts on vaccine discourse will discuss the information context of the vaccine debate, political influence, and attitudes towards science and vaccines against the backdrop of social media. This panel is expected to contribute to the field of information science by invoking a conversation on social media, an important information communication technology, as a field of study that inter-connects the most current vaccine conversation with theories of partisan behavior of health information and affordance of technology. This panel is sponsored by SIG SM.

show abstract

Sentiment, Contents, and Retweets: A Study of Two Vaccine-Related Twitter Datasets

Abstract: Engaging social media key opinion leaders to facilitate health education about vaccination in their tweets may allow reaching a wider audience online.

Cited by 140 publications

References 28 publications

Pedagogical Demonstration of Twitter Data Analysis: A Case Study of World AIDS Day, 2014

Pedagogical Demonstration of Twitter Data Analysis: A Case Study of World AIDS Day, 2014

Tweeting the #flushot: Beliefs, Barriers, and Threats During Different Periods of the 2018 to 2019 Flu Season

Social Media, Vaccines, and Partisan Division of Health Information

Contact Info

Product

Resources

About