#研究分享#【哪儿有流感?社交媒体告诉你】

#研究分享#【哪儿有流感?社交媒体告诉你】圣地亚哥州立大学研究者收集了人们在Twitter上发送的带有“感冒”等字眼的信息及其发送者的用户名和地点等,发现在11个城市中,有9个城市流感患者的比例与这些信息有关。他们认为,医学工作者能通过社交媒体获悉何时何处正爆发流感,并据此做好准备。

8b87ee0259f5c070c592edcf41b83591

 

Geography experts believe Twitter could help medical professionals learn where and when severe flu outbreaks are occurring in real time

San Diego State University researchers recorded 161,821 tweets containing the word ‘flu’ and 6,174 containing ‘influenza’ for their study

They discovered that nine out of 11 cities studied showed a ‘significant’ correlation between tweets about flu and the rates of flu-like illnesses

 

Twitter might be best known as the place to go for day-to-day updates about people’s lives and celebrity selfies, but it could also be used as a health tool, researchers claim.

Geography experts have discovered that posts on the social network predicted flu outbreaks in different parts of the U.S.

They believe Twitter could help medical professionals learn where and when severe flu outbreaks are occurring in real time so they can prepare for busy periods, which typically occur during the winter months.

 

The researchers, led by San Diego State University geography professor Ming-Hsiang Tsou, examined tweets that originated from a 17 mile radius of 11 different U.S. cities between June and December 2012.

Whenever people tweeted the keywords ‘flu’ or ‘influenza,’ a computer programme recorded characteristics about the tweets, including the username and location of the people who sent them as well as whether they were original tweets or retweets and whether they linked to a website.

 

From June 2012 to the beginning of December, the algorithm recorded 161,821 tweets containing the word ‘flu’ and 6,174 containing ‘influenza’.

The researchers compared the location data of those tweets to data on the flu virus rates recorded in the relevant cities and counties.

They discovered that of the 11 cities where tweets were examined, there was a ‘significant’ correlation between tweets about flu and the rates of flu-like illnesses in nine of the cities.

 

Twitter also seemed to be able to predict outbreaks in five of the cities: San Diego, Denver, Jacksonville, Fort Worth and Seattle, as the tweets recorded instances of illness before they were officially documented and reported by cities and counties.

‘Traditional procedures take at least two weeks to detect an outbreak. With our method, we're detecting daily,’ he said.

The Centre for Disease Control and Prevention defines flu season as the period from October through May, usually peaking around February, but the unpredictability of when and where outbreaks may occur makes it difficult for hospitals and regional health centres to prepare.

 

There is about a two week lag in the time it takes for hospitals to notice a sharp rise in flu patients and the U.S. centre issuing a warning.

The researchers found original tweets and tweets without website links proved more predictive than retweets or those that did include links, possibly because original tweets are more likely to reflect individuals posting about their own symptoms.

Professor Tsou believes his technique, which is detailed in the Journal of Medical Internet Research, could allow officials to more quickly and efficiently direct resources to outbreak zones and better contain the spread of the disease.

‘There is the potential to use social media to really improve the way we monitor the flu and other public health concerns,’ he said.

Professor Tsou is not on his own in thinking social media could be used as a powerful predictive medical tool.

In 2011, scientists from Pennsylvania State University used Twitter to track attitudes towards the flu vaccination and labelled them as being positive, neutral or negative.

 

U.S. mobile conferencing company Citrix has also built a microsite to track tweets about flu to examine how it affects workplaces.

It said ‘lurgy’ is the highest flu-related hashtag on Twitter, according to a UK study it commissioned by YouGov and that ‘office martyrs’ are the top cause of widespread illness in offices.

The survey found 46 per cent of office workers and 56 per cent of senior business people blame employees who ‘soldier on’ for spreading workplace germs.

Around a quarter of UK office works said their colleagues do not take time off when they are ill as they worry about their workload, while just over half of workers agree the office would be more productive if ill colleagues stayed at home.

 

文章标题:Twitter can predict where FLU outbreaks will occur and could help doctors prepare for busy times

网址:http://www.dailymail.co.uk/sciencetech/article-2511960/Twitter-predict-FLU-outbreaks-occur-help-doctors-prepare-busy-times.html#ixzz2lWc5fkMh

来源:每日邮报


1 条评论

  1. wuyijia说道:

    感谢分享+http://weibo.com/1711479641/AkcSjuv7N



无觅相关文章插件