Argumentative Writing Support

Argumentative Writing Support

Motivation

Formulating persuasive and well-formed arguments is a challenging task and a crucial aspect in writing skills acquisition. However, current writing support is limited to feedback about grammar or spelling and there is no system that provides formative feedback about argumentative writing. In this project, we aim to research novel methods for assisting authors in writing persuasive arguments with respect to the following questions:

  • Is my argument well structured and comprehensible?
  • Are the given reasons relevant for my claim?
  • Does my argument include sufficient support for being persuasive?

Goals

  • Create tools which aid in improving argumentation quality
  • Develop methods for identifying argumentation structures in text
  • Investigate novel models which automatically assess argumentation quality
  • Provide formative feedback about argumentation

Methods

The research methods of Argumentative Writing Support (AWS) include three consecutive steps/tasks:

1. Identification of argumentation structure: Separation of argumentative and non-argumentative text units and recognition of argument components by means of state-of-the-art Natural Language Processing (NLP) techniques.

2. Assessment of argumentation quality: Development of novel techniques for identifying flaws in the argumentation structure, assessing the type of reasoning, and evaluating appropriateness of the given support.

3. Formative feedback: Integration of the methods in writing environments and visualization of quality flaws in the text document in order to support authors in revising their arguments.

Data

Partners

  • Holtzbrinck Publishing Group
  • Macmillan Science & Education

People

  • Prof. Dr. Iryna Gurevych, Principal Investigator
  • Christian Stab, Doctoral Researcher