Argumentative discourse concepts as revealed by traversing a graph

Abstract

Recent advances in computing and Internet technologies, together with the advent of the Web 2.0 era have resulted in the development of a plethora of online tools, such as forums and social networking applications, which offer people an unprecedented level of flexibility and convenience to participate in complex argumentative discourses of diverse interest. However, these tools do not enable an intelligent analysis of the related content. Aiming to address this issue, this paper presents preliminary work on the exploitation of Neo4j graph platform for managing well-established argumentation elements. The proposed high level and scalable approach facilitates the discovery of latent and arbitrarily long and complex argumentation in argument graphs, as well as its meaningful exploitation towards gaining insights.