Extraction of Online Discussion Structures for Automated Facilitation Agent

Abstract

This paper proposes an approach that aims to extract the discussion structure from large-scale text-based online discussions. The ultimate goal is to develop an automated facilitation agent that is able to extract discussion structures from large-scale online discussions. To support this facilitation agent, an extraction approach is needed. Towards this end, we adopt the issue-based information system (IBIS), as a suitable format for structuring online discussions. In this context, we model the task of extracting an IBIS structure as it consists of node extraction and link extraction. Towards this end, a deep neural network based approach is employed in order to perform these two extraction subtasks. In order to evaluate the proposed approach, a set of experiments has been conducted on the data collected from the discussions in the online discussion support system called D-Agree. The experimental results show that the proposed approach is efficient for extracting online discussion structures.