What can we learn about the Ebola outbreak from tweets?

doi:10.1016/j.ajic.2015.02.023

American Journal of Infection Control

Volume 43, Issue 6, 1 June 2015, Pages 563-571

https://doi.org/10.1016/j.ajic.2015.02.023 Get rights and content

Background

Twitter can address the challenges of the current Ebola outbreak surveillance. The aims of this study are to demonstrate the use of Twitter as a real-time method of Ebola outbreak surveillance to monitor information spread, capture early epidemic detection, and examine content of public knowledge and attitudes.

Methods

We collected tweets mentioning Ebola in English during the early stage of the current Ebola outbreak from July 24-August 1, 2014. Our analysis for this observational study includes time series analysis with geologic visualization to observe information dissemination and content analysis using natural language processing to examine public knowledge and attitudes.

Results

A total of 42,236 tweets (16,499 unique and 25,737 retweets) mentioning Ebola were posted and disseminated to 9,362,267,048 people, 63 times higher than the initial number. Tweets started to rise in Nigeria 3-7 days prior to the official announcement of the first probable Ebola case. The topics discussed in tweets include risk factors, prevention education, disease trends, and compassion.

Conclusion

Because of the analysis of a unique Twitter dataset captured in the early stage of the current Ebola outbreak, our results provide insight into the intersection of social media and public health outbreak surveillance. Findings demonstrate the usefulness of Twitter mining to inform public health education.

Section snippets

Tweet corpus

Tweets mentioning EVD were collected daily from Twitter (https://twitter.com/) via a Google Chrome–based version of NCapture (QSR International; Melbourne, Australia) from July 24-August 1, 2014. Key words used for the identification of EVD-related data included #Ebola, #EbolaOutbreak, #EbolaVirus, and #EbolaFacts. Key word selection for our data corpus was informed by Twitter search trends and suggested search functions. Data elements collected for each tweet included content, time stamp,

Trends of information spread

A total of 42,236 tweets mentioning the recent EVD outbreak were posted (16,499 unique and 25,737 retweets) and disseminated to 9,362,267,048 people from July 24-August 1, 2014 (Fig 1). On July 24, the baseline of 382 posted tweets (128 unique and 254 retweets) was disseminated to 1,502,743 Twitter users. On July 26, with the announcement of the EVD infection of an American physician, the baseline number increased 8-fold to 3,222 posted tweets (1,574 unique and 1,648 retweets), with a 644-fold

Discussion

The conceptual framework of public health surveillance and action identifies the essential need for active surveillance during re-emerging rare infections such as EVD. The framework also demonstrates how health systems can link outbreak surveillance to action through data information messages.¹⁴ The current study reveals how tweets can be collected and analyzed to support early warning systems for epidemic trends and to inform data information messages for health education interventions.²⁸ The

Conclusions

It is important to emphasize the ongoing and critical need for effective health education messages to accompany news alerts regarding EVD and other global outbreaks. With the recent cases of EVD in the United States, several confusing and flawed messages were issues by the CDC, prompting lawmakers to question the agency's ability to handle the EVD health crisis.³⁶ Although information is widely disseminated, the American people remain confused and fearful. Alternatively, there is something to

Acknowledgments

We thank Elaine L. Larson, RN, PhD, and Jacqueline A. Merrill, RN, MPH, PhD, for their insights in initiation of the project. We were able to capture the rare but critical data before the Ebola outbreak to contribute to the early detection of the outbreak using Twitter. We thank Suzanne R. Bakken, RN, PhD, for her support in several years of training for the authors to learn the analytic skills of Twitter.

References (38)

R. Ansumana et al.
Ebola in Sierra Leone: a call for action
Lancet
(2014)
A. Green
Ebola emergency meeting establishes new control centre
Lancet
(2014)
S.J. McNabb et al.
Applying a new conceptual framework to evaluate tuberculosis surveillance and action performance and measure the costs, Hillsborough County, Florida, 2002
Ann Epidemiol
(2004)
J.C. Bosley et al.
Decoding twitter: surveillance and trends for cardiac arrest and resuscitation communication
Resuscitation
(2013)
S. Yoon et al.
A practical approach for content mining of tweets
Am J Prev Med
(2013)
J. Giles
‘Unlike’ the FBI on Facebook
New Sci
(2012)
D. Gatherer
The 2014 Ebola virus disease outbreak in West Africa
J Gen Virol
(2014)
N. Dolan
Infectious disease surveillance update
Lancet
(2014)
I. Torjesen
Two doctors die from Ebola and lives of others under threat in West Africa
BMJ
(2014)
IHR Emergency Committee on Ebola outbreak in West Africa. Ebola virus disease update – Senegal. Global alert and response: disease outbreak news
(2014)

E. Izadi

Ebola death toll rises to 2,296 as Liberia struggles to keep up

(2014)

A. Sifferlin

WHO: more than 1,000 killed in Ebola outbreak

(2014)

M.G. Dixon et al.

Ebola viral disease outbreak West Africa 2014

MMWR Morb Mortal Wkly Rep

(2014)

H. Feldmann

Ebola - a growing threat?

N Engl J Med

(2014)

J.M. Drazen et al.

Ebola and quarantine

N Engl J Med

(2014)

Centers for Disease Control and Prevention. Viral hemorrhagic fevers. Fact sheet. Georgia;...

P. Calain

Exploring the international arena of global public health surveillance

Health Policy Plan

(2007)

R.G. Ridley

Research on infectious diseases requires better coordination

Nat Med

(2004)

H.I. Hall et al.

Lexicon, definitions, and conceptual framework for public health surveillance

MMWR Surveill Summ

(2012)

Cited by (182)

Tracking attention about COVID-19 vaccines on twitter and newspapers: A dynamic agenda-setting approach
2024, Telematics and Informatics Reports
This study delves into the intricate dynamics of agenda-setting between Twitter and elite news media concerning COVID-19 vaccines. A comprehensive dataset comprising 501,531 US-based, English-language tweets and 7,282 news headlines extracted from The New York Times and The Washington Post was collected from January 1, 2020, to April 30, 2021. To uncover the temporal evolution of content topics, Latent Dirichlet Allocation (LDA) was employed alongside sentiment analysis to gage corresponding valence levels. Granger causality tests were then conducted on the time series of topic sizes and valence scores from tweets and news headlines to explore the intermedia agenda-setting effects. The LDA analysis identified 13 topics, with Twitter discourse predominantly focusing on the top five ranked topics, while news headlines exhibited a more even distribution across all topics. The Granger causality tests revealed tweets-to-news Granger causality for four topics, news-to-tweets Granger causality for four topics, and mutual influence for the remaining five topics. Consequently, the directions of the agenda-setting effects varied depending on the specific discussions' topics. The findings indicated that elite news media wielded greater influence over socially impactful aspects of COVID-19 vaccination, while Twitter exhibited an agenda largely independent of elite news media, centering on highly personal facets of COVID-19 vaccination. Furthermore, the transfer of salience in topics was more pronounced compared to valence.
Social media user behavior analysis applied to the fashion and apparel industry in the big data era
2023, Journal of Retailing and Consumer Services
With the rapid development of the Internet and new media, the enormous data from social media and other public platforms have attracted increasing attention to user behavior research. Fashion is a hot topic for both the general public and the social economy, so there is great potential for exploring and manipulating social media data for the development of the fashion industry in the current era. This paper aims to explore the current status of social media user behavior analysis applied to the fashion and apparel industry for advanced product development, branding strategy planning and the resolution of other decision-making problems in the big data context. First, articles were retrieved from the database "Web of Science". With the assistance of experts, 201 articles were determined for further study. Next, the evolution of hot topics within the domain was visualized and discussed through bibliometric analysis. Then, the application of social media data in the fashion domain was investigated, and common data mining methods were discussed. Finally, the paper summarized the development status of social media user behavior analysis (SMUBA) applied to the fashion and apparel industry and put forward the future prospect under the framework of mass customization in the big data era.
Are Twitter sentiments during COVID-19 pandemic a critical determinant to predict stock market movements? A machine learning approach
2023, Scientific African
The problem of stock market prediction is a challenging task owing to its complex nature and the numerous indirect factors at play. The sentiments regarding socio-political issues such as wars and pandemics can affect stock prices. The spread of the COVID-19 pandemic continues to take a toll on the economy and fluctuations in sentiment of the concerns about the health impacts of the disease can be captured from the microblogging platform, Twitter. We examined how these sentiments during the Covid-19 pandemic and the health impacts arising from the disease along with other macroeconomic indicators provide useful information to predict the stock indices in a more accurate manner. We developed a machine learning model namely, long-short term memory (LSTM) networks to predict the impact of the Covid-19 induced sentiments on the stock values of different sectors in the United States and India. We did the same predictions using the timeseries statistical models such as autoregressive moving average model and the linear regression model. We then compared the performance of the LSTM and the timeseries statistical models to find that the machine learning model has produced more accurate predictions of the stock indices. The performance of the models across the sectors and between the United States and India are compared to draw economic inferences.
Early warning for emerging infectious disease outbreaks: Digital disease surveillance for public health preparedness and response
2023, Accelerating Strategic Changes for Digital Transformation in the Healthcare Industry: Volume 2
Emerging infectious diseases such as SARS, Ebola virus, and COVID-19 are a significant threat to health globally. These global epidemics result in increased media consumption by the public for information and expressing their thoughts and ideas through internet search engines and social media. Analyzing people's internet search behavior regarding health-related information and social media use can guide real-time surveillance and early warning systems for emerging diseases and help in health preparedness and response by public health authorities and hospitals. There have been studies using social media and other digital data for the detection of infectious disease outbreaks. However, there are several methodological challenges with digital disease surveillance, such as confounding, nonrepresentativeness, nonindependence of data, sampling bias, and changes in search algorithms. There is a need for robust research methods to address these challenges and design digital disease surveillance systems that could help in the early response and containment of emerging epidemics.
A non-invasive machine learning mechanism for early disease recognition on Twitter: The case of anemia
2022, Artificial Intelligence in Medicine
Social media sites, such as Twitter, provide the means for users to share their stories, feelings, and health conditions during the disease course. Anemia, the most common type of blood disorder, is recognized as a major public health problem all over the world. Yet very few studies have explored the potential of recognizing anemia from online posts. This study proposed a novel mechanism for recognizing anemia based on the associations between disease symptoms and patients' emotions posted on the Twitter platform. We used k-means and Latent Dirichlet Allocation (LDA) algorithms to group similar tweets and to identify hidden disease topics. Both disease emotions and symptoms were mapped using the Apriori algorithm. The proposed approach was evaluated using a number of classifiers. A higher prediction accuracy of 98.96 % was achieved using Sequential Minimal Optimization (SMO). The results revealed that fear and sadness emotions are dominant among anemic patients. The proposed mechanism is the first of its kind to diagnose anemia using textual information posted on social media sites. It can advance the development of intelligent health monitoring systems and clinical decision-support systems.
Learning Through the Social Conditions Experienced by Orphans During #Covid-19 with Social Media Mining
2024, SSRN

View all citing articles on Scopus

: Author contributions: Yoon and Odlum designed the study. All of the authors drafted the manuscript, critically revised the manuscript for important intellectual content, had full access to all of the data in the study, and take responsibility for the integrity of the data and the accuracy of the data analysis.

: Disclaimer: This study used publically available data, and analyses meet the criterion for exemption §46.101(b)4 research, involving the collection or study of existing data, documents, records, pathologic specimens, or diagnostic specimens, if these sources are publicly available, or if the information is recorded by the investigator in such a manner that subjects cannot be identified, directly or through identifiers linked to the subjects.

: Conflicts of interest: None to report.

View full text

Major articleWhat can we learn about the Ebola outbreak from tweets?

Background

Methods

Results

Conclusion

Section snippets

Tweet corpus

Trends of information spread

Discussion

Conclusions

Acknowledgments

Lancet

Lancet

Ann Epidemiol

Resuscitation

Am J Prev Med

New Sci

The 2014 Ebola virus disease outbreak in West Africa

J Gen Virol

Infectious disease surveillance update

Lancet

Two doctors die from Ebola and lives of others under threat in West Africa

BMJ

IHR Emergency Committee on Ebola outbreak in West Africa. Ebola virus disease update – Senegal. Global alert and response: disease outbreak news

Ebola death toll rises to 2,296 as Liberia struggles to keep up

WHO: more than 1,000 killed in Ebola outbreak

Ebola viral disease outbreak West Africa 2014

MMWR Morb Mortal Wkly Rep

Ebola - a growing threat?

N Engl J Med

Ebola and quarantine

N Engl J Med

Exploring the international arena of global public health surveillance

Health Policy Plan

Research on infectious diseases requires better coordination

Nat Med

Lexicon, definitions, and conceptual framework for public health surveillance

MMWR Surveill Summ

Major article
What can we learn about the Ebola outbreak from tweets?