On the ground validation of online diagnosis with Twitter and medical records

摘要: Social media has been considered as a data source for tracking disease. However, most analyses are based on models that prioritize strong correlation with population-level disease rates over determining whether or not specific individual users actually sick. Taking different approach, we develop novel system social-media detection at the level using sample of professionally diagnosed individuals. Specifically, making an accurate influenza diagnosis individual's publicly available Twitter data. We find about half (17/35 = 48.57%) in our were sick explicitly discuss their Twitter. By developing meta classifier combines text analysis, anomaly detection, and social network able to diagnose greater than 99% accuracy even if she does her health.