Visual Linguistic Analysis of Political Discussions: Measuring Deliberative Quality

Abstract

This article reports on a Digital Humanities research project which is concerned with the automated linguistic and visual analysis of political discourses with a particular focus on the concept of deliberative communication. According to the theory of deliberative communication as discussed within political science, political debates should be inclusive and stakeholders participating in these debates are required to justify their positions rationally and respectfully and should eventually defer to the better argument. The focus of the article is on the novel interactive

Rhetorical strategies in German argumentative dialogs

“…Investigating rhetorical structuring on a larger scale will, therefore, have benefits for argumentation mining as well as discourse processing in general. Given the vibrant field of Visual Analytics in linguistics [15,16,19,20,33,38,39], this area will come up with new ways of presenting a more holistic view of single arguments as well as the process of argumentation in large amounts of high-dimensional data. Taken together, we arrive at a much richer and more detailed interpretation of the discourse and the web of information that comprises natural language argumentation.…”

“…These argumentative units are marked explicitly by the 38 discourse connectives given in Table 1 which are taken from the Potsdam Commentary Corpus [46], complemented with our own curated list of items. 3 To extract the information from the dialogs, we use the VisArgue pipeline, a parsing pipeline that reliably annotates the spans triggered by discourse connectives and several rhetorical devices [2,12,15, for more details on the annotation of argumentative units and the performance of the system see Section 5.1]. The relative frequencies of argumentative units that contain one or more particles are shown in Table 2.…”

“…We make crucial use of the VisArgue pipeline [2,12,15], a linguistically motivated, high-quality parsing pipeline that automatically identifies, disambiguates and annotates discourse information in transcribed natural speech, among them information coming from discourse particles.…”

Interactive Visual Analysis of Transcribed Multi-Party Discourse

“…Argumentation Feature Fingerprinting In an attempt to measure the deliberative quality of discourse (Gold and Holzinger, 2015), we use the annotations discussed in Section 3 and create a fingerprint of all utterances, the Argumentation Glyph. The glyph maps the four theoretic dimensions of deliberation in its four quadrants which are separated by the axes: NW (Accommodation), NE (Atmosphere & Respect), SE (Participation), SW (Argumentation & Justification).…”

Generative Data Models for Validation and Evaluation of Visualization Techniques

“…One example is a pixel visualization of properties extracted from the annotated digital historical corpus of Icelandic [98], whereby data is generated on the basis of the annotation, but the visualization reflects a further level of abstraction from the underlying data [103,104]. Another example is work conducted on understanding argumentation in political debates [41], where a variety of different types of information can be accessed, visualized, and explored interactively. Many of the properties that are accessed from the underlying data are the result of sophisticated linguistic and computational analysis and have been produced via generative models of various kinds.…”