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

TL;DR

This paper investigates what makes conversations meaningful and how to design conversational agents that support long-term relationships, highlighting the importance of social dynamics, trust, and context in human-agent interactions.

Contribution

It provides empirical insights into user perceptions of conversation, emphasizing the need to redefine design parameters for more effective and relational conversational agents.

Findings

People see a clear distinction between social and functional conversation roles.

Long-term trust and bond are valued in human conversations.

Users question the necessity of bond and common ground in agent communication.

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.