Case Study: Centers for Disease Control and Prevention (CDC) achieves predictive flu surveillance with Luminoso's text analytics

The Centers for Disease Control and Prevention predicts spread of the flu with text analytics

The Centers for Disease Control and Prevention (CDC) needed faster, more predictive insight into flu spread than traditional reports from doctors and hospitals could provide. The Situational Awareness Branch wanted to analyze real-time conversational text to detect emerging cases and severity trends—including illnesses people didn’t explicitly label—to make models timely rather than reactive.

Using Luminoso’s text analytics, the CDC integrated historical quantitative data with real-time social media and conversational text, identifying subtle signals (for example, “shopping for NyQuil” or the pill emoji) that correlated with flu cases. The system processed over 8,000 social posts per minute, improved prediction accuracy, and enabled the CDC to distinguish flu-specific language, assess vaccine and treatment effectiveness, and track the severity, duration, and spread of the current strain.

Centers for Disease Control and Prevention (CDC)