Medical News Today: Mining Ebola tweets yields valuable outbreak information

Stock SectorJune 1, 20156min3
<div>Researchers who analyzed tens of thousands of tweets sent during early stages of the current Ebola outbreak conclude Twitter mining can usefully inform public health education.</div>
Last year, in the 3 days before the outbreak was officially announced, over 60 million people received tweets about the Ebola outbreak in West Africa, say the authors of a new study published in the American Journal of Infection Control that investigates the useful role that Twitter can play in outbreak monitoring and control.
map of Nigeria
In the 3 days prior to Nigeria’s official announcement about Ebola, Twitter users had already shared around 1,500 tweets about the outbreak.

Social media allow users to play active roles in spreading news. Users can share insights, opinions, fears and ideas, outside the contexts of conventional public health channels.

Twitter is a popular social media application where users can send short messages – called “tweets” – of up to 140 characters. The ability to “retweet” a received message allows for rapid and broad distribution of information.

Worldwide, over 58 million tweets a day are generated by a diverse and growing community of over 645 million registered Twitter users.

Timely information gathering is crucial in outbreak surveillance and an important part of limiting disease spread and ensuring appropriate public health education.

Researchers are increasingly turning to social media as rich seams of data, which, if mined appropriately, can help capture epidemic trends and other important surveillance information.

For example, a geography professor at San Diego State University has developed a social media monitoring model that uses Twitter to track the spread of influenza.

The Ebola outbreak in West Africa – which started in March 2014 – is now the largest and deadliest occurrence of Ebola virus disease to date, with over 11,000 lives claimed and over 27,000 reported cases.

For their study, two researchers from Columbia University School of Nursing in New York, analyzed Ebola-related tweets posted over a week in the early stages of the West African outbreak – from July 24th to August 1st 2014.

During that week, Nigeria reported its first case of Ebola virus disease, Sierra Leone declared a national state of emergency and the first American was diagnosed with the deadly disease.

Before official announcements were made by the Nigerian authorities, the World Health Organization and the US Centers for Disease Control and Prevention, people were sharing news about Ebola cases via Twitter.

‘A useful resource for spreading breaking health news’

In the 3 days prior to the Nigerian Ministry of Health’s official announcement of the country’s first confirmed case of Ebola, Twitter users had already shared around 1,500 tweets about Ebola.

For example, among the first tweets at this time in Nigeria were messages like “#EbolaVirus 1st case discovered Lagos, pls spread the word” and “Guys, #EbolaVirus is in Lagos. Be informed. Be careful.”

During the week covered by the study, the researchers analyzed over 42,000 tweets – 16,500 of which were unique and over 25,500 were retweets. Over the week, the spread of tweets multiplied by 63 times to over 4 billion user messages worldwide.

The researchers analyzed the timings, distribution and contents of the tweets. The content analysis – using natural language processing techniques – revealed that Twitter users’ main topics of discussions were risk factors, prevention education, disease trends, spread and location of Ebola, and compassion for countries in Africa.

The authors note that the number of Twitter users in African countries like Nigeria has increased exponentially, and it is “clear that Twitter is a useful resource for spreading breaking health news in these West African countries.”

They conclude that mining tweets could be a useful way to inform public health education:

“The results of this analysis indicate how Twitter can be used to support early warning systems in outbreak surveillance efforts in settings where surveillance systems are not optimal.”

MNT also recently learned how health-related tweets may have the potential to be helpful for hospitals. In a study led by the University of Arizona, researchers developed a model that showed with 75% accuracy how Twitter predicted asthma visits to the ER of a hospital on a given day.

Written by





Web Design BangladeshBangladesh Online Market