Single or Multiple Conversational Agents? - An Interactional Coherence Comparison

Explore a 25-minute conference talk from the ACM CHI Conference on Human Factors in Computing Systems that compares single and multiple conversational agents in terms of interactional coherence. Delve into the findings of a Wizard of Oz experiment investigating user interactions with chatbots in travel planning scenarios. Discover insights on conversation content, user speech patterns, and reported impressions in both single- and multi-chatbot environments. Learn about the implications for designing chatbot systems, including the potential redundancy of meta-chatbots and the importance of considering different interactional aspects for each scenario. Gain valuable knowledge on the future of conversational AI and its impact on user experience in multi-expertise tasks.

Introduction
Chatbots
Specific Tasks
MetaChat Bot
Multiparty Conversation
Objectives
Experiment
Research Question 1
Research Question 2
Research Question 3
Findings
Takeaway
Next Steps
Questions