Scientists from Pennsylvania State University say they’ve developed a way to find Twitter posts that identify viral illnesses, InformationWeek reports. In a recently published paper, “On the Ground Validation of Online Diagnosis with Twitter and Medical Records,” researchers say they’ve created “a system for making an accurate influenza diagnosis based on an individual’s publicly available Twitter data.” The researchers say they were able to determine, with 99-percent accuracy, whether an influenza outbreak was occurring by combining text analysis, anomaly detection and social network analysis. In 2008, similarly, Google began estimating flu infections by tracking flu-related search terms.
Full Story