Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems 2018
DOI: 10.1145/3173574.3173765
|View full text |Cite
|
Sign up to set email alerts
|

Single or Multiple Conversational Agents?

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
7
1

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 40 publications
(9 citation statements)
references
References 39 publications
1
7
1
Order By: Relevance
“…On the other hand, some players preferred the simplicity of contact to a single agent and perceived to succeed faster in the game this way, even though the duration of the responses were the same in both versions. They experienced the multi-agent interaction as too complex and overstraining, which is in line with results from a study on a multi-chatbot system [7]. This seems conclusive considering the brevity of the exposure to the multi-agent system with roughly 10 minutes per session.…”
Section: Discussionsupporting
confidence: 86%
See 1 more Smart Citation
“…On the other hand, some players preferred the simplicity of contact to a single agent and perceived to succeed faster in the game this way, even though the duration of the responses were the same in both versions. They experienced the multi-agent interaction as too complex and overstraining, which is in line with results from a study on a multi-chatbot system [7]. This seems conclusive considering the brevity of the exposure to the multi-agent system with roughly 10 minutes per session.…”
Section: Discussionsupporting
confidence: 86%
“…They encountered reluctance from the users when the agents conversed with each other as this was considered unnecessary in a task-oriented setting [17]. In another study on the user's behavior towards multiagent systems, Chaves and Gerosa [7] analyzed the change in speech and reactions of users to a multiplicity of chatbots compared to a single chatbot. Their results showed that the multiplicity of chatbots had no significant effect on the conversation structure or its content.…”
Section: Multi-agent Interactionmentioning
confidence: 99%
“…The Priority maxim suggests that power dynamics are at play in human-AI interactions at a turn-taking level, where humans are assumed to take priority in initiating turns. Developing proper turn-taking strategies is notoriously difficult in AI design (Portela & Granell-Canut 2017;Liao et al 2016;Chaves & Gerosa 2018). Taking the Priority maxim into account could help resolve some of these issues, where designers can take human expectations of their priority into account.…”
Section: Resultsmentioning
confidence: 99%
“…Distributed collaboration of chatbots is a real need. Intent routing, turn taking, context switching, server handling and fulfilling users' satisfactions are the major problems of developing a multi-chatbot system that adopt the distributed collaboration approach [53,54]. In addition, the collaboration feature is implemented with the use of a single orchestration chatbot that orchestrates the conversation and there is not always a direct collaboration between the distributed chatbots.…”
Section: Distributed Collaboration In Multi-chatbot Systemsmentioning
confidence: 99%