Argument Analysis and Visualization

Theoretical (Analytical):

Practical (Implementation):

Literature Work:


Overview and Problem Statement

Argumentation, and computational argument mining, are popular topics at the intersection of computer science and linguistics. Argument mining is concerned with the automated extraction of argumentative phrases from text documents: claims and premises, the stance of arguments, and attack- and support-relations between arguments. 

Typical results of argument mining are large, tree-like structures. As such, they are difficult to interpret and analyse due to their size. Visual Analytics can help to make these structures explorable, and guide users in their argumentation analysis. An integral part of such systems are visualizations that show how the arguments are connected and relate them to the underlying original text. 

Tasks

  • Review common argumentation frameworks
  • Develop and implement appropriate argumentation visualizations
  • Create a visual analytics system for interactive refinement of argumentation mining results
  • Create machine learning models for argument detection and classification

Requirements

  • Good knowledge about information visualization and natural language processing.
  • Good programming skills in Java and JavaScript/D3.

Scope/Duration/Start

  • Scope: Master
  • 6 Month Project, 6 Month Thesis
  • Start: immediately

Contact