An Agent that Facilitates Crowd Discussion

Takayuki Ito,Rafik Hadfi,Shota Suzuki

doi:10.1007/s10726-021-09765-8

Takayuki Ito, Rafik Hadfi + Show 1 more

Open Access

https://doi.org/10.1007/s10726-021-09765-8

Copy DOI

Abstract

Online discussion platforms are perceived as the next-generation method of citizen involvement. Such platforms can collect, integrate, and synthesize opinions to achieve social good. Crowd-scale platforms are being developed and deployed in social experiments that involve citizens and local governments. In such platforms, human facilitation is often used to preserve the quality of the discussions. Human facilitators often face difficulties when the discussions grow in size. In this paper, we present “D-agree,” a crowd-scale discussion support system based on an automated facilitation agent. The agent extracts discussion structures from online discussions, analyzes them, and posts facilitation messages. We conducted small- and large-scale social experiments in Japan to assess the social impact of the platform. The results showcase the success of our automated facilitation agents in gathering valuable opinions from citizens. In addition, our experiments highlight the effect of an automated facilitation agent on online discussions. In particular, we find that combining the agent facilitator with human facilitators leads to higher user satisfaction.

Highlights

Crowd-scale discussion platforms are posed to be the next-generation platforms for democratic citizen involvement
We looked at how many Issue-Based Information System (IBIS) elements are generated in a discussion and how many of these are generated as a result of the facilitation messages
Issue 1 was raised by the participant, and the automated facilitation agent identified this post as an issue

Summary

Introduction

Crowd-scale discussion platforms are posed to be the next-generation platforms for democratic citizen involvement. Kyoto University, Yoshida‐Honmachi, Kyoto 606‐8501, Japan 2 Nagoya Institute of Technology, Gokiso, Showa‐ku 466‐8555, Nagoya, Japan An example of such platforms is the “COLLAGREE” system, with its ability to work jointly with human facilitators to promote crowd-scale online discussions (Sengoku et al 2016; Ito et al 2015, 2014; Ito 2018). Despite their ability to promote citizen participation, human facilitators face cognitive challenges due to the possible scale of discussions and the complexity of the themes discussed (Kawase et al 2018; Nishida et al 2018, 2017). The automated facilitation agent extracts the structure of the discussion, analyzes it, and posts targeted messages to effectively facilitate the discussion

Methods

Results

Discussion

Conclusion