Using Biased Social Samples for Disaster Response: Extended Abstract

摘要

Social media is an important data source. Every day, billions of posts, likes, and connections are created by people around the globe. By monitoring social media platforms, we can observe important topics, as well as find new topics of discussion as they emerge. This is never more apparent than in disaster scenarios, where people post in real-time about what is unfolding on the ground. Social media posts have been used in many disaster scenarios such as Hurricane Sandy to monitor the needs of, and to relay important information to those effected. However, within this source of information there are natural forms of bias. While these platforms are critically important, the way social media platforms divulge their data can cause bias to those studying information produced on that site, and can completely skew what those studying the platform can see. This is a problem as critical information may not reach first responders, or may also be skewed when it does. We will discuss the different types of bias that can occur on social media data as well as different strategies to mitigate that bias.