System identification (2nd ed.): theory for the user
System identification (2nd ed.): theory for the user
ACM Computing Surveys (CSUR)
Dengue surveillance based on a computational model of spatio-temporal locality of Twitter
Proceedings of the 3rd International Web Science Conference
Proceedings of the 4th ACM SIGSPATIAL International Workshop on GeoStreaming
| Hi-index | 0.00 |
Our vision is to achieve faster and near real time detection and prediction of the emergence and spread of an influenza epidemic, through sophisticated data collection and analysis of Online Social Networks (OSNs) such as Facebook, MySpace, and Twitter. In particular, we present the design of a system called SNEFT (Social Network Enabled Flu Trends), which will be developed in a 12-month SBIR (Small Business Innovation Research) project funded by the National Institutes of Health (NIH). We describe the innovative technologies that will be developed in this project for collecting and aggregating OSN data, extracting information from it, and integrating it with mathematical models of influenza. One of the monitoring tools used by the Centers for Disease Control and Prevention (CDC) is reports of Influenza-Like Illness (ILI) cases; these reports are authoritative but typically have a delay of one to two weeks due to the largely manual process. We describe the SNEFT prototype in the context of predicting ILI cases well in advance of the CDC reports. We observe that OSN data is individually noisy but collectively revealing, and speculate on other applications that can potentially be enabled by OSN data collection and analysis.