What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents


Conference paper


L. Clark, Nadia Pantidi, Orla Cooney, Philip R. Doyle, Diego Garaialde, Justin Edwards, Brendan Spillane, Christine Murad, Cosmin Munteanu, V. Wade, Benjamin R. Cowan
International Conference on Human Factors in Computing Systems, 2019

ACM Link ArXiv
Cite

Cite

APA   Click to copy
Clark, L., Pantidi, N., Cooney, O., Doyle, P. R., Garaialde, D., Edwards, J., … Cowan, B. R. (2019). What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents. In International Conference on Human Factors in Computing Systems.


Chicago/Turabian   Click to copy
Clark, L., Nadia Pantidi, Orla Cooney, Philip R. Doyle, Diego Garaialde, Justin Edwards, Brendan Spillane, et al. “What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents.” In International Conference on Human Factors in Computing Systems, 2019.


MLA   Click to copy
Clark, L., et al. “What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents.” International Conference on Human Factors in Computing Systems, 2019.


BibTeX   Click to copy

@inproceedings{l2019a,
  title = {What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents},
  year = {2019},
  journal = {International Conference on Human Factors in Computing Systems},
  author = {Clark, L. and Pantidi, Nadia and Cooney, Orla and Doyle, Philip R. and Garaialde, Diego and Edwards, Justin and Spillane, Brendan and Murad, Christine and Munteanu, Cosmin and Wade, V. and Cowan, Benjamin R.}
}

Abstract

Conversational agents promise conversational interaction but fail to deliver. Efforts often emulate functional rules from human speech, without considering key characteristics that conversation must encapsulate. Given its potential in supporting long-term human-agent relationships, it is paramount that HCI focuses efforts on delivering this promise. We aim to understand what people value in conversation and how this should manifest in agents. Findings from a series of semi-structured interviews show people make a clear dichotomy between social and functional roles of conversation, emphasising the long-term dynamics of bond and trust along with the importance of context and relationship stage in the types of conversations they have. People fundamentally questioned the need for bond and common ground in agent communication, shifting to more utilitarian definitions of conversational qualities. Drawing on these findings we discuss key challenges for conversational agent design, most notably the need to redefine the design parameters for conversational agent interaction.