"TwitterCracy: Exploratory Monitoring of Twitter Streams for the 2016 U.S. Presidential Election Cycle", M. Atif Qureshi, Arjumand Younus, Derek Greene. Proc. ECML PKDD 2016: Machine Learning and Knowledge Discovery in Databases, 2016. [Link]

TwitterCracy is an exploratory search system that allows users to monitor and navigate the Twitter streams of political entities. It aims to facilitate voters and analysts, by keeping them aware of the key agenda issues that are of interest to politicians, as reflected by their ongoing activity on Twitter. The system's exploratory capabilities stem from the application of lightweight time-series based clustering, together with biased PageRank to extract facets from tweets, which are presented in a manner that facilitates exploration.

We haved applied TwitterCracy to a case study based around the 2016 U.S Presidential Election, analyzing the activity of 635 relevant politicians and political organizations on Twitter during the campaign. See the video below for a demonstration of its use.