Chatbots Facilitating Consensus-Building in Asynchronous Co-Design

In The 35th Annual ACM Symposium on User Interface Software and Technology, UIST 2022
Aalto User Interfaces Lab
How to facilitate consensus-building with chatbots?
  • Background: Consensus-building is a group decision-making process that can resolve conflicts between group members' opinions.
  • Challenge: Consensus-building requires high effort from human facilitators in guiding group mebmers idea exchange and increasing their willingness to commit to group decisions.
  • Solution: Conversational agents like chatbots could facilitate consensus-building by eliciting fairness and mutual effort in dialogue:
    • Giving a fair chance to everyone to voice their own ideas.
    • Promoting solutions that could satisfy both groups in conflict.
    • Presenting other group members' ideas as inspirations.
    • Encouraging everyone to consider the other group members' opposite ideas as solutions.
  • Result: Our empirical evaluation study showed that chatbots can be promising facilitators for consensus-buildling that can increase everyone's willingness to commit to group decisions even to the ones that conflicts with personal opinions.
Abstract

Consensus-building is an essential process for the success of co-design projects. To build consensus, stakeholders need to discuss conflicting needs and viewpoints, converge their ideas toward shared interests, and grow their willingness to commit to group decisions. However, managing group discussions is challenging in large co-design projects with multiple stakeholders. In this paper, we investigate the interaction design of a chatbot that can mediate consensus-building conversationally. By interacting with individual stakeholders, the chatbot collects ideas to satisfy conflicting needs and engages stakeholders to consider others' viewpoints, without having stakeholders directly interact with each other. Results from an empirical study in an educational setting (N = 12) suggest that the approach can increase stakeholders' commitment to group decisions and maintain the effect even on the group decisions that conflict with personal interests. We conclude that chatbots can facilitate consensus-building in small-to-medium-sized projects, but more work is needed to scale up to larger projects.

Conversation design
An example of chatbot-facilitated consensus-building in co-design that involves no direct communication between stakeholders. In the system, the chatbot stages the discussion (A) and presents conflicts (B). It then invites users to make aninitial suggestion (C), perform self-assessment (D), review others' suggestions that are similar to (E) and in conflict with the user's own (F), take others' perspective (G), and make the final suggestion (H).
Materials
  • Our implementation (in Python) of the chatbot facilitator is available on Github along with instructions:
    Github Page
  • Introductory video at UIST 2022:

Publication
paper

PDF, 4.2 MB
Joongi Shin, Michael A. Hedderich, Andrés Lucero, Antti Oulasvita. 2022. Chatbots Facilitating Consensus-Building in Asynchronous Co-Design Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (UIST ’22). 

							
@inproceedings{shin22codesign-ai,
	author = {Shin, Joongi and Hedderich, Michael A. and Lucero, Andr\'{e}S and Oulasvirta, Antti},
	title = {Chatbots Facilitating Consensus-Building in Asynchronous Co-Design},
	year = {2022},
	isbn = {9781450393201},
	publisher = {Association for Computing Machinery},
	address = {New York, NY, USA},
	url = {https://doi.org/10.1145/3526113.3545671},
	doi = {10.1145/3526113.3545671},
	booktitle = {Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology},
	articleno = {78},
	numpages = {13},
	keywords = {Chatbot, Co-Design, Consensus-building},
	location = {Bend, OR, USA},
	series = {UIST '22}
}
Contact

For questions and further information, please contact:

Joongi Shin

Email:
joongishin@gmail.com

Acknowledgements: The research was supported by the Aalto University Department of Communications and Networking, the Finnish Center for Artificial Intelligence (FCAI), Academy of Finland (grants ‘Human Automata’ and ‘BAD’), and a fellowship within the IFI programme of the German Academic Exchange Service (DAAD).