Augmented Argumentation

Abstract

Distributed groups of people, both in industry and the military, face a sequence of ad-hocdecisions whose quality has dramatic impa ct on the organization. Increasingly, the discussion and subsequent decisions are made online after multiple rounds of arguments and rebuttals, but tracking these distributed arguments is extremely time consuming and error prone. We propose to build a decision sup port system that augments people, who are discussing complex decisions in unstructured English, and aids a leader in making the ulti mate decision. A central aspect of our solution will comprise natural language processing (NLP) tools to analyze arguments, claims a nd counter claims. These tools will link corresponding arguments and counter arguments from different people (and from the same peop le over time). For evaluation, we propose to first apply our methods to the academic paper review process, using data from OpenRevie w.

Document Details

Document Type
DoD Grant Award
Publication Date
Sep 07, 2021
Source ID
N000142112707

Entities

People

  • Daniel S. Weld

Organizations

  • Office of Naval Research
  • United States Navy
  • University of Washington

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Educational Psychology
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML