JSAI2019
Jun 4 - Jun 7, 2019TOKI MESSE, Niigata Convention Center
JSAI2019
Jun 4 - Jun 7, 2019TOKI MESSE, Niigata Convention Center
[2F1-E-3-02]Extraction of Online Discussion Structures for Automated Facilitation Agent
〇Shota Suzuki1, Naoko Yamaguchi1, Tomohiro Nishida1, Ahmed Moustafa1, Daichi Shibata1, Kai Yoshino1, Kentaro Hiraishi1, Takayuki Ito1(1. Nagoya Institute of Technology)
Keywords:
Natural Language Processing,Deep Learning,Automated Agent,Consensus Building
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.