As the most recent spread of the Zika virus continues, there is an increasing presence of Zika related information on social media platforms such as Twitter. The information found on Twitter provides a unique opportunity to obtain real-time news and firsthand accounts about a variety of subjects and events but there is potential for the spread of misinformation. During crisis events, it is important for users to be able to find accurate and timely information regarding safety precautions and potential threats. This research provides a valuable opportunity to detect misinformation related to the Zika virus on Twitter through a chained gradient boosted model using a unique set of descriptive features associated with Tweet formation, author credentials, subject matter, and author intention.