Skip to content

DEliBot – Deliberation Enchancing Bot

Project Description

Deliberation is the dialogue between a group that facilitates careful weighing of information, providing adequate speaking opportunities and bridging the differences among participants’ diverse ways of thinking and problem-solving. It is traditionally explored in psychology, where researchers examine the conditions under which groups can make better decisions together. Previous research has shown that a small focus group can outperform wisdom-of-the-crowd. Further, researchers have shown that under some conditions, a group can outperform even the most knowledgeable individual, also known as the assembly bonus effect. However, not all groups are equal, and not every group deliberates well.

To address this, we introduce the concept of Deliberation Enhancing Bots – DEliBots. The primary objective of a DEliBot is to improve the group’s decision-making by providing a framework for good deliberation practices. To achieve this, we leverage the concept of conversational probing – asking questions that stimulate further discussion and innovative thinking within a group setting. A DEliBot is an artificial moderator that models group dynamics and encourages effective deliberation without providing solutions. Furthermore, in 2022 we organised the Deliberation4Good workshop, which gathered interest from people across industries and disciplines. Stay tuned for the next edition of the Deliberation4Good.

There are many challenges in building a DEliBot – from defining what is an improvement through finding the right time to intervene, to generating a helpful and productive response. Herein, we present our current efforts, data and code resources, as well as public outreach of the DEliBot project. Meet the team behind DEliBot and reach out for any questions, collaborations, and applications!


News

  • [17.10.2023] DeliData presented at CSCW’2024
  • [26.01.2023] DEliBot project presentation at the Natural Language Processing Special Interest Group @The Alan Turing Institute
  • [09.09.2022] “What makes you change your mind? An empirical investigation in online group decision-making conversations” is presented at SIGDIAL’2022. [Link to slides]
  • [26.07.22] Our paper “What makes you change your mind? An empirical investigation in online group decision-making conversations” was accepted at SIGDIAL’2022 (to be presented in September). Preprint: https://arxiv.org/abs/2207.12035

DEliData

A dataset for deliberation in multi-party problem solving

DeliToolkit

Tools, models, and resources that we used in our DEliBot endaevours.

pip install delitoolkit

DialogueDen

Data platform for synchronous data collection in the wild. Contact us at the email bellow to discuss use cases and code repository.


Let’s talk about constructive discussions!

Contact us at: Georgi.Karadzhov[at]cl.cam.ac.uk