What Animates Political Debates ? Analyzing Ideological Perspectives in Online Debates between Opposing Parties

Internet and social media created a public space for online debate on political and social issues. A debate is defined as a formal discussion on a set of related issues in which opposing perspectives and arguments are put forward. In this paper, we aim to develop automated perspective discovery techniques which would contribute to the understanding of frames that drive contention between radical right and liberal political actors in Eastern Europe using Slovakia as a case study. Based on computational analyses of their online corpus, we develop an analytical tool to identify contentious frames between ideological opposites and to predict online escalation. A frame is the packaging of an element of rhetoric in such a way as to encourage certain interpretations and to discourage others. Our experimental data comprises nearly 10,000 documents downloaded from the official websites of radical right and liberal Slovak political parties spanning a decade between 2004-2014. Our perspective discovery algorithm not only identifies contentious vs. ignored frames, but it also utilizes these frames to predict online escalation with an accuracy of 82.8% (F-measure). We also present qualitative analysis of the resultant frames.