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

By L. Clark, Nadia Pantidi, Orla Cooney, Philip R. Doyle, Diego Garaialde, Justin Edwards, Brendan Spillane, C. Murad, Cosmin Munteanu, Vincent P. Wade and 1 more. International Conference on Human Factors in Computing Systems, 2019

467 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Social Psychology

View Paper: https://www.semanticscholar.org/paper/b8905ad435d440bab6a2b0c5d2db39a078dbf281

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Social Psychology

Citations in the corpus

Empathy Is All You Need: How a Conversational Agent Should Respond to Verbal Abuse (2020, background): “People considered conversational agents as a tool or servant that supports humans and were resistant to the idea of becoming friends with CA [20, 23].”
My Chatbot Companion - a Study of Human-Chatbot Relationships (2021, background): “Similarly, Clark et al. (2019) did not find evidence of relationship formation between users and chatbots and attributed this to the strictly task-oriented nature of interactions with conversational agents such as Alexa.”
“It’s Kind of Like Code-Switching”: Black Older Adults’ Experiences with a Voice Assistant for Health Information Seeking (2021, background): “Currently, people are able to change the voices of the assistant to be a familiar voice or media personality such as Issa Rae, but the actual interaction style or dynamic is far from resembling human-to-human conversation – so much so that scholars have suggested that voice assistants agents can onl”