Authors: Fabian Sperrle, Rita Sevastjanova, Rebecca Kehlbeck, Mennatallah El-Assady
Abstract: Argumentation Mining addresses the challenging tasks of identifying argumentative text fragments and extracting their relationships. Fully automated solutions do not reach satisfactory accuracy due to their insufficient incorporation of human intuition and domain knowledge. Therefore, experts currently rely on time-consuming manual annotations. In this paper, we present a Visual Analytics approach that augments the manual annotation process by reacting to the users’ interactions and continuously suggesting which text fragments to annotate next. The accuracy of those automatic suggestions is improved over time by incorporating language modeling and learning from user interactions, training a measure of argument similarity. Based on a long-term collaboration with domain experts we identify and model five high-level analysis tasks. We enable close-reading and note-taking, annotation of arguments, argument reconstruction, extraction of argument relations, and exploration of argument graphs. To avoid context switches, we transition between all views through seamless semantic zooming, visually anchoring all close- and distant-reading layers. We evaluate our system through a two-stage expert user study based on a corpus of presidential debates. The results show that experts prefer our system over existing solutions due to the speedup provided by the automatic suggestions and the tight integration of text and graph views.