Forecasting influenza-like illness dynamics for military populations using neural networks and social media.
Forecasting influenza-like illness dynamics for military populations using neural networks and social media.
复制标题
DOI：
10.1371/journal.pone.0188941
复制
发表时间：
2017
期刊：
影响因子：
3.7
通讯作者：
Corley CD
中科院分区：
文献类型：
--
作者：
Volkova S;Ayton E;Porterfield K;Corley CD
这项工作是第一个利用递归神经网络从社交媒体数据中提取的各种语言信号预测流感样疾病（ILI）动态的工作。与依赖于历史ILI数据的时间序列分析和最先进的机器学习模型的其他方法不同，我们构建并评估了基于长短期记忆（LSTM）单元的神经网络架构的预测能力，这些单元能够在2011 - 2014年流感季节进行临近预报（实时预测）和预测（预测未来）ILI动态。为了建立我们的模型，我们整合了人们在社交媒体上发布的信息，例如，主题、嵌入、单词语法、风格模式以及使用主题标签和提及的通信行为。然后，我们定量评估不同社交媒体信号的预测能力，并使用不同的评估指标集将最先进的回归模型与神经网络的性能进行对比。最后，我们结合联合收割机ILI和社会媒体信号，建立一个联合神经网络模型ILI动态预测。与现有的大多数工作不同，我们特别专注于开发用于地方而不是国家ILI监测的模型，特别是针对26个美国和6个国际地点的军事而不是一般人群。并分析模型性能如何取决于每个位置可用的社交媒体数据量。我们的方法展示了几个优点：（a）与以前使用的回归模型相比，依赖于在社交媒体数据上训练的LSTM单元的神经网络架构产生了最佳性能。(b)以前未被充分探索的语言和沟通行为特征比社交媒体中表达的风格和主题信号更能预测ILI动态。(c)专门从社交媒体信号学习的神经网络模型产生与从ILI历史数据学习的模型相当或更好的性能，因此，来自社交媒体的信号可以潜在地用于准确预测ILI历史数据不可用的区域的ILI动态。(d)从ILI和社交媒体信号的组合中学习的神经网络模型显著优于仅依赖ILI历史数据的模型，这增加了ILI动态预测的替代公共来源的巨大潜力。(e)位置特定模型优于先前使用的位置无关模型，仅限美国。(f)根据可用的社交媒体数据量和ILI活动模式，不同地理位置的预测结果差异很大。(g)模型性能随着每个地理位置可用的更多推文而提高，例如，对于具有更多推文的位置，误差变得更低并且皮尔逊分数变得更高。
This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs) units capable of nowcasting (predicting in “real-time”) and forecasting (predicting the future) ILI dynamics in the 2011 – 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a) Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns. (g) Model performance improves with more tweets available per geo-location e.g., the error gets lower and the Pearson score gets higher for locations with more tweets.
登录
查看更多内容
影响因子：
4.3
作者：
Riley, Pete;Ben-Nun, Michal;Riley, Steven
通讯作者：
Riley, Steven
影响因子：
4.3
作者：
Santillana M;Nguyen AT;Dredze M;Paul MJ;Nsoesie EO;Brownstein JS
通讯作者：
Brownstein JS
DOI：
10.3390/ijerph7020596
发表时间：
2010-02
影响因子：
--
作者：
Corley CD;Cook DJ;Mikler AR;Singh KP
通讯作者：
Singh KP
DOI：
10.4269/ajtmh.2012.11-0597
发表时间：
2012-01-01
影响因子：
3.3
作者：
Chunara, Rumi;Andrews, Jason R.;Brownstein, John S.
通讯作者：
Brownstein, John S.
影响因子：
6
作者：
Blei, DM;Ng, AY;Jordan, MI
通讯作者：
Jordan, MI