Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2841–2847 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 2841 Who Sides With Whom? Towards Computational Construction of Discourse Networks for Political Debates Sebastian Pad´o1, Andr´e Blessing1, Nico Blokker2, Erenay Dayanik1, Sebastian Haunss2, and Jonas Kuhn1 1IMS, University of Stuttgart, Germany 2SOCIUM, University of Bremen, Germany Abstract Understanding the structures of political de- bates (which actors make what claims) is es- sential for understanding democratic political decision-making. The vision of computational construction of such discourse networks from newspaper reports brings together political sci- ence and natural language processing. This paper presents three contributions towards this goal: (a) a requirements analysis, linking the task to knowledge base population; (b) a first release of an annotated corpus of claims on the topic of migration, based on German newspa- per reports; (c) initial modeling results. 1 Introduction Democratic decision making can follow broadly two logics: In a technocratic, depoliticized mode, decision-making is carried out by administrative staff and experts. However, arguably most political decisions affecting large populations attract public attention and thus happen in a politicized mode, in which public debates accompany decision making (de Wilde, 2011; Z¨urn, 2014; Haunss and Hofmann, 2015). Understanding the structure and evolution of political debates is therefore essential for un- derstanding democratic decision making. Recent innovations that combine political claims analysis (Koopmans and Statham, 1999) with network sci- ence under the name of discourse network analysis (Leifeld, 2016a) allow us to systematically analyze the dynamics of political debates based on the an- notation of large newspaper corpora. So far, such studies have been carried out manually. In this paper, we outline the road towards using computational methods from natural language pro- cessing for the construction of discourse networks – working towards an integrated methodological framework for Computational Social Science. We make three contributions: (a) a requirements analy- sis; (b) a manually annotated corpus of claims from affiliation network actors claims actor network (discourse coalition) concept network (argumentative cluster) c1 c2 c3 c5 c4 a1 a2 a3 a5 a4 Figure 1: Actor, affiliation, and concept networks debates about migration found in German newspa- per reports; (c) initial modeling results that already demonstrate the usefulness of computational meth- ods in this context. 2 Discourse Networks: Actors and Claims Discursive interventions are one element among several that influence policy making (Schmidt and Radaelli, 2004). But the exact mechanisms of polit- ical discourse and under which condition discursive interventions do or do not translate into political de- cisions are largely unknown. At least there seems to be a general agreement that the formation and evolution of discourse coalitions is a core mecha- nism (Hajer, 1993; Sabatier and Weible, 2007). A discourse coalition can be generally defined as “a group of actors who share a social construct” (Hajer, 1993, p. 43). Political Claims Analysis (Koopmans and Statham, 1999) provides a frame- work in which claims, that is demands, proposals, criticisms, or decisions in the …

Content truncated to 500 words