Tweeting During the Covid-19 Pandemic: Sentiment Analysis of Twitter Messages by President Trump
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
In this article, we utilize VADER, a rule-based model, to perform sentiment analysis of tweets by President Donald Trump during the early spread of the Covid-19 pandemic across the United States, making it the worst-hit country in the world. We discover a statistically significant negative correlation between the sentiment of his messages and the number of Covid-19 cases in the United States, indicating an effect on the tone of his tweets as the pandemic took its toll on American lives and economy. Furthermore, we also witness a gradual shift from positive to negative sentiment in his messages mentioning China and coronavirus together.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Many of the negative hashtags have been perpetuated by public figures such as the former President of America and the right-wing media [35,36].”
From The evolving role of preprints in the dissemination of COVID-19 research and their impact on the science communication landscape (2021) · cites this paper as [35]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Chen, Q., Min, C., Zhang, W., Wang, G., Ma, X., & Evans, R. (2020) · Computers in Human Behavior · doi:10.1016/j.chb.2020.106380 · Cited by 652
Enli, G. (2017) · European Journal of Communication · doi:10.1177/0267323116682802 · Cited by 637 · cited 1×
“We observe a somewhat similar approach with respect to China, where he tries to employ a deprofessionalized and amateurish style in his Twitter communication to appear authentic [11].”
BackgroundTwitter for crisis communication: lessons learned from Japan's tsunami disaster
Acar, A., & Muraki, Y. (2011) · International Journal of Web Based Communities · doi:10.1504/ijwbc.2011.041206 · Cited by 419 · cited 1×
“Some of the first studies to evaluate Twitter usage during natural disasters looked at user tweets in the course of Japan’s earthquake and tsunami of 2011 [1].”
BackgroundTakahashi, B., Tandoc, E. C., & Carmichael, C. (2015) · Computers in Human Behavior · doi:10.1016/j.chb.2015.04.020 · Cited by 375
World leaders' usage of twitter in response to the COVID-19 pandemic: A content analysis
Rufai, S. R., & Bunce, C. (2020) · Journal of Public Health · doi:10.1093/pubmed/fdaa049 · Cited by 308
Pourebrahim, N., Sultana, S., Edwards, J., Gochanour, A., & Mohanty, S. (2019) · International Journal of Disaster Risk Reduction · doi:10.1016/j.ijdrr.2019.101176 · Cited by 195 · cited 1×
“Since then, the use of Twitter during natural disasters and crises has continued to rise [20, 27].”
BackgroundAnalysis of political discourse on twitter in the context of the 2016 US presidential elections
Yaqub, U., Chun, S. A., Atluri, V., & Vaidya, J. (2017) · Government Information Quarterly · doi:10.1016/j.giq.2017.11.001 · Cited by 192 · cited 1×
“His frequent use of the micro-blogging site and his influence as President of the United States of America have led to various scientific studies evaluating his Twitter messages [10, 29].”
BackgroundSelf-citationPotter, S., & Wickler, G. (2008) · Cited by 170
Rao, H. R., Vemprala, N., Akello, P., & Valecha, R. (2020) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2020.102187 · Cited by 150 · cited 1×
“They conveyed reassurances by replying to troubling tweets, issuing alerts on progress of virus, and outlining ways to protect against the pandemic [21].”
Background‘Going negative’: An APPRAISAL analysis of the rhetoric of Donald Trump on Twitter
Ross, A. S., & Caldwell, D. (2019) · Language & Communication · doi:10.1016/j.langcom.2019.09.003 · Cited by 147
Clarke, I., & Grieve, J. (2019) · PLOS ONE · doi:10.1371/journal.pone.0222062 · Cited by 134
Using tweets to support disaster planning, warning and response
Landwehr, P. M., Wei, W., Kowalchuck, M. J., & Carley, K. M. (2016) · Safety Science · doi:10.1016/j.ssci.2016.04.012 · Cited by 112 · cited 1×
“Various tools and applications have developed over time that utilized actionable information extracted from Twitter for disaster relief efforts [5, 17].”
BackgroundPolitical news and stock prices: evidence from Trump’s trade war
Burggraf, T., Fendel, R., & Huynh, T. L. D. (2019) · Applied Economics Letters · doi:10.1080/13504851.2019.1690626 · Cited by 105
Under his thumb the effect of president Donald Trump’s Twitter messages on the US stock market
Brans, H., & Scholtens, B. (2020) · PLoS ONE · doi:10.1371/journal.pone.0229931 · Cited by 62
Analysis and visualization of subjectivity and polarity of Twitter location data
Yaqub, U., Sharma, N., Pabreja, R., Chun, S. A., Atluri, V., & Vaidya, J. S. (2018) · Annual International Conference on Digital Government Research · doi:10.1145/3209281.3209313 · Cited by 43 · cited 1×
“This has led to a rise in research studies employing sentiment analysis to gauge public mood and opinion utilizing Twitter data [8, 15, 30].”
BackgroundSelf-citationWeb-based application for sentiment analysis of live tweets
Sharma, N., Pabreja, R., Yaqub, U., Atluri, V., Chun, S. A., & Vaidya, J. S. (2018) · Annual International Conference on Digital Government Research · doi:10.1145/3209281.3209402 · Cited by 35 · cited 1×
“Furthermore, advancements in natural language processing and machine learning have enabled researchers to automate analysis of large text datasets, created by millions of users [14, 25].”
BackgroundSelf-citationFirms’ performance and board size: A simultaneous approach in the European and American contexts
Augusto, M., Pascoal, R., & Reis, P. M. N. (2019) · Applied Economics Letters · doi:10.1080/13504851.2019.1659487 · Cited by 18
Political News and Stock Prices: Evidence from Trump’s Trade WarPreprint
Fendel, R., Burggraf, T., & Huynh, T. L. D. (2019) · SSRN Electronic Journal · Cited by 2
Research works printed but not linked: 8
- Al Amin, Imran Hossain, Aysha Akther, and Kazi Masudul Alam. 2019. Bengali VADER: A sentiment analysis approach using modified VADER. In Proceedings of the 2019 International Conference on Electrical, Computer, and Communication Engineering (ECCE'19). IEEE, Los Alamitos, CA, 1-6.
- Nadya A. Calderon, Brian Fisher, Jeff Hemsley, Billy Ceskavich, Greg Jansen, Richard Marciano, and Victoria L. Lemieux. 2015. Mixed- initiative social media analytics at the world bank: Observations of citizen sentiment in Twitter data to explore "trust" of political actors and state institutions and its relationship to social protest. In Proceedings of the 2015 IEEE International Conference on Big Data (Big Data'15). IEEE, Los Alamitos, CA, 1678-1687.
- Justin H. Gross and Kaylee T. Johnson. 2016. Twitter taunts and tirades: Negative campaigning in the age of Trump. PS: Political Science & Politics 49, 4 (2016), 748-754.
- Clayton J. Hutto and Eric Gilbert. 2014. VADER: A parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the 8th International AAAI Conference on Weblogs and Social Media.
- Sardar Haider Waseem Ilyas, Zainab Tariq Soomro, Ahmed Anwar, Hamza Shahzad, and Ussama Yaqub. 2020. Analyzing Brexit's impact using sentiment analysis and topic modeling on Twitter discussion. In Proceedings of the 21st Annual International Conference on Digital Government Research. 1-6. Digital Government: Research and Practice, Vol. 2, No. 1, Article 1. Publication date: November 2020.
- Hae-Young Kim. 2013. Statistical notes for clinical researchers: Assessing normal distribution (2) using skewness and kurtosis. Restora- tive Dentistry & Endodontics 38, 1 (2013), 52-54.
- Sahar Sohangir, Nicholas Petty, and Dingding Wang. 2018. Financial sentiment lexicon analysis. In Proceedings of the 2018 IEEE 12th International Conference on Semantic Computing (ICSC'18). IEEE, Los Alamitos, CA, 286-289.
- Chris Wells, Dhavan Shah, Josephine Lukito, Ayellet Pelled, Jon C. W. Pevehouse, and JungHwan Yang. 2020. Trump, Twitter, and news media responsiveness: A media systems approach. New Media & Society 22, 4 (2020), 659-682.
Cited by
Fraser, N., Brierley, L., Dey, G., Polka, J. K., Pálfy, M., Nanni, F., & Coates, J. A. (2021) · PLOS Biology · doi:10.1371/journal.pbio.3000959 · Cited by 555
“Many of the negative hashtags have been perpetuated by public figures such as the former President of America and the right-wing media [35,36].”
BackgroundSentiment analysis of Twitter texts using Machine learning algorithms
BARZENJI, H. (2021) · Academic Platform Journal of Engineering and Smart Systems · doi:10.21541/apjes.939338 · Cited by 20
“In [22] USSAMA YAQUB applied sentiment analysis on trump’s tweets during the early appearance of the coronavirus pandemic (i.”
Public Health Policy Monitoring through Public Perceptions: A Case of COVID-19 Tweet Analysis
Li, C.-Y., Renda, M., Yusuf, F., Geller, J., & Chun, S. A. (2022) · Information · doi:10.3390/info13110543 · Cited by 17
Sharma, S., Sharma, R. R., & Datta, A. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3225216 · Cited by 21
“The focus of the third dimension is looking at information and meta-data in the tweets that influence their visibility, such as words used, hashtags, likes to study whether there are distinctive characteristics across Misleading and Non-Misleading tweets.”
Background“Spine to the future”—A narrative review of anatomy engagement
Taylor, A. M., & Wessels, Q. (2024) · Anatomical Sciences Education · doi:10.1002/ase.2417 · Cited by 9
“91,92 This is likely going to increase the amount of time allocated and needed to dispel these challenges.”
Background
Metadata
- Authors
- Yaqub, U.
- Affiliations
- Lahore University of Management Sciences (PK)
- Corresponding author
- Yaqub, Ussama
- ORCID
- Yaqub, Ussama
- Venue
- Digital Government Research and Practice
- Published
- 2020-11-09
- Volume
- 2
- Issue
- 1
- Pages
- 1-7
- ISSN
- 2639-0175 (ISSN-L)
- 2691-199X
- OpenAlex
- W3095252820
- Cited by
- 16
- References
- 18
- Citations by year
- 2025: 1 · 2024: 4 · 2023: 2 · 2022: 4 · 2021: 5
- FWCI
- 1.08
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Digital Government Research and Practice (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › Communication › Communication and COVID-19 Impact
- Social Sciences › Cultural Studies › Discourse Analysis and Cultural Communication
- Keywords
- Donald Trump, Twitter, COVID-19 pandemic, sentiment analysis, VADER, presidential communication, COVID-19 case counts, China, political rhetoric, public health crisis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.