What is it about?
We designed, developed, and evaluated CommunityBots — a multi-agent chatbot platform where each chatbot handles a different domain individually to elicit public input. To manage conversation across multiple topics and chatbots, we proposed a novel Conversation and Topic Management (CTM) mechanism that handles topic-switching and chatbot-switching based on user responses and intentions. Our evaluation demonstrates that CommunityBots participants were significantly more engaged, provided higher-quality responses, and experienced fewer conversational interruptions while conversing with multiple chatbots in the same session. We also found that the visual cues integrated with the interface helped the participants better understand the functionalities of the CTM mechanism, which enabled them to perceive changes in textual conversation, leading to better user satisfaction.
Featured Image
Photo by Volodymyr Hryshchenko on Unsplash
Why is it important?
One of the emergent areas where chatbots can be beneficial is the timely collection of public input during major societal crises, such as COVID-19. Using a multi-agent chatbot system gives opportunities for eliciting multi-faceted and multiscalar public input, but there remain unsolved challenges regarding the design, effectiveness, and user experience. In this study, we investigated the design and development of multi-agent chatbots for eliciting multi-faceted and multi-scalar input and improving conversational engagement across multiple domains.
Perspectives
Read the Original
This page is a summary of: CommunityBots: Creating and Evaluating A Multi-Agent Chatbot Platform for Public Input Elicitation, Proceedings of the ACM on Human-Computer Interaction, April 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3579469.
You can read the full text:
Contributors
The following have contributed to this page