In February 2016, World Health Organization declared the Zika outbreak aPublic Health Emergency of International Concern. With developing evidence itcan cause birth defects, and the Summer Olympics coming up in the worstaffected country, Brazil, the virus caught fire on social media. In this work,use Zika as a case study in building a tool for tracking the misinformationaround health concerns on Twitter. We collect more than 13 million tweets --spanning the initial reports in February 2016 and the Summer Olympics --regarding the Zika outbreak and track rumors outlined by the World HealthOrganization and Snopes fact checking website. The tool pipeline, whichincorporates health professionals, crowdsourcing, and machine learning, allowsus to capture health-related rumors around the world, as well as clarificationcampaigns by reputable health organizations. In the case of Zika, we discoveran extremely bursty behavior of rumor-related topics, and show that, once thequestionable topic is detected, it is possible to identify rumor-bearing tweetsusing automated techniques. Thus, we illustrate insights the proposed toolsprovide into potentially harmful information on social media, allowing publichealth researchers and practitioners to respond with a targeted and timelyaction.
展开▼
