Skip to Main Content U.S. Department of Energy
Deep Science Agile Initiative

News and Highlights

#Flu. Research highlighted in Scientific American.

Svitlana Volkova

The April 2018 Scientific American features work by NSD's Svitlana Volkova (Computing and Analytics Division) and team on predicting influenza outbreaks using social media. In the article, "#Flu: Mining Social Media to Predict Outbreaks," science writer Rachel Berkowitz compares Volkova and team's work with previous work on flu outbreak prediction, which searched social media for illness-related words. Volkova's team instead used deep learning to correlate non-illness-related words in Twitter feeds with patterns of flu outbreaks. The algorithm "learned" to predict outbreaks up to two weeks in advance accurately. Such prediction may enable officials to take proactive public health measures that could save lives.

After PLOS One published the article by Volkova and co-authors Katie Porterfield and Ellyn Ayton last December, Berkowitz wrote the Public Health section article for Scientific American.

Berkowitz visited PNNL in 2012.

Read more about Volkova's efforts and the PLOS One article.

Deep Learning