| Abstract: |
| The data generated from social media can be used for predictions in a rapid and accurate
fashion. In recent years many researchers have explored real-time streaming data from Twitter for a broad range of
applications such as predicting flu trends. In this talk, we present our design and implementation of a prototype system to collect flu related twitter data. Further we use partial differential equation models and neural networks to predict epidemic outbreaks based on the twitter data. We correlate the results with official statistics from Center for Disease Control and Prevention (CDC). These results demonstrate that the system can be used to real-timely monitor the spread of influenza |
|