nEmesis: Which Restaurants Should You Avoid Today?

摘要: Computational approaches to health monitoring and epidemiology continue evolve rapidly. We present an end-to-end system, nEmesis, that automatically identifies restaurants posing public risks. Leveraging a language model of Twitter users' online communication, nEmesis finds individuals who are likely suffering from foodborne illness. People's visits modeled by matching GPS data embedded in the messages with restaurant addresses. As result, we can assign each venue "health score" based on proportion customers fell ill shortly after visiting it. Statistical analysis reveals our inferred score correlates ( r = 0.30) official inspection Department Health Mental Hygiene (DOHMH). investigate joint associations multiple factors mined DOHMH violation scores find over 23% variance be explained factors. demonstrate readily accessible used detect cases illness timely manner. This approach offers inexpensive way enhance current methods monitor food safety (e.g., adaptive inspections) identify potentially problematic venues near-real time.