Using Twitter hashtags to gauge real-time changes in public opinion: An examination of the 2016 US presidential election

Abstract

Polls have long been a tool for gauging public opinion, whether in general or in relation to specific events. Poll results, however, take a few days to be collected and published. Trending twitter hashtags, in contrast, are keywords that capture public sentiments about current events and could serve as a data source for gauging real-time changes in public opinion. This paper examines trending Twitter hashtags following the release of James Comey’s letter to Congress shortly before the 2016 US presidential election day. I find that trending Twitter hashtags mirror and, more importantly, precede the poll results of the same period.