National and local influenza surveillance through Twitter: an analysis of the 2012-2013 influenza epidemic.
National and local influenza surveillance through Twitter: an analysis of the 2012-2013 influenza epidemic.
复制标题
DOI：
10.1371/journal.pone.0083672
复制
发表时间：
2013
期刊：
影响因子：
3.7
通讯作者：
Dredze M
中科院分区：
文献类型：
--
作者：
Broniatowski DA;Paul MJ;Dredze M
社交媒体已被提议作为流感监测的数据来源，因为它们有可能提供对数百万条包含个人健康信息的地理定位短消息的实时访问。然而，社交媒体监测系统的准确性随着媒体的关注而下降，因为媒体的关注增加了“闲谈”——关于流感但与实际感染无关的信息——掩盖了流感真正流行的迹象。本文总结了我们最近开发的流感感染检测算法，该算法可以自动区分相关推文和其他聊天，并描述了我们目前在2012-2013年整个流感季节积极部署的流感监测系统。我们的目标是分析该系统在最近的2012-2013年流感季节期间的表现，并在多个地理粒度层面分析其表现，这与过去侧重于国家或区域监测的研究不同。我们系统的流感流行估计值与美国疾病控制和预防中心的监测数据（r = 0.93, p < 0.001）以及纽约市卫生和精神卫生部的监测数据（r = 0.88, p < 0.001）密切相关。我们的系统以85%的准确率检测流感流行方向的每周变化（增加或减少），比一个更简单的模型提高了近两倍，证明了明确区分感染微博与其他聊天的效用。
Social media have been proposed as a data source for influenza surveillance because they have the potential to offer real-time access to millions of short, geographically localized messages containing information regarding personal well-being. However, accuracy of social media surveillance systems declines with media attention because media attention increases “chatter” – messages that are about influenza but that do not pertain to an actual infection – masking signs of true influenza prevalence. This paper summarizes our recently developed influenza infection detection algorithm that automatically distinguishes relevant tweets from other chatter, and we describe our current influenza surveillance system which was actively deployed during the full 2012-2013 influenza season. Our objective was to analyze the performance of this system during the most recent 2012–2013 influenza season and to analyze the performance at multiple levels of geographic granularity, unlike past studies that focused on national or regional surveillance. Our system’s influenza prevalence estimates were strongly correlated with surveillance data from the Centers for Disease Control and Prevention for the United States (r = 0.93, p < 0.001) as well as surveillance data from the Department of Health and Mental Hygiene of New York City (r = 0.88, p < 0.001). Our system detected the weekly change in direction (increasing or decreasing) of influenza prevalence with 85% accuracy, a nearly twofold increase over a simpler model, demonstrating the utility of explicitly distinguishing infection tweets from other chatter.
登录
查看更多内容
影响因子：
3.7
作者：
Chew C;Eysenbach G
通讯作者：
Eysenbach G
DOI：
10.1056/nejmp0900702
发表时间：
2009-05-21
期刊：
The New England journal of medicine
影响因子：
--
作者：
Brownstein JS;Freifeld CC;Madoff LC
通讯作者：
Madoff LC
DOI：
10.1056/nejmp1307752
发表时间：
2013-08-01
期刊：
The New England journal of medicine
影响因子：
--
作者：
Salathé M;Freifeld CC;Mekaru SR;Tomasulo AF;Brownstein JS
通讯作者：
Brownstein JS
影响因子：
6.4
作者：
Dredze, Mark
通讯作者：
Dredze, Mark
DOI：
10.1371/currents.outbreaks.bb1e879a23137022ea79a8c508b030bc
发表时间：
2013-06-21
期刊：
PLoS currents
影响因子：
--
作者：
Nsoesie, Elaine;Mararthe, Madhav;Brownstein, John
通讯作者：
Brownstein, John