Towards Human-centered Proactive Conversational Agents

TL;DR

This paper emphasizes the importance of designing human-centered proactive conversational agents that prioritize human needs, ethics, and social considerations, proposing a new taxonomy to guide future research and development.

Contribution

It introduces a novel taxonomy focusing on Intelligence, Adaptivity, and Civility to guide the development of human-centered proactive conversational agents.

Findings

Proactive systems must balance initiative with user comfort.

A new taxonomy helps categorize key dimensions of human-centered PCAs.

Research opportunities include integrating ethics and social awareness.

Abstract

Recent research on proactive conversational agents (PCAs) mainly focuses on improving the system's capabilities in anticipating and planning action sequences to accomplish tasks and achieve goals before users articulate their requests. This perspectives paper highlights the importance of moving towards building human-centered PCAs that emphasize human needs and expectations, and that considers ethical and social implications of these agents, rather than solely focusing on technological capabilities. The distinction between a proactive and a reactive system lies in the proactive system's initiative-taking nature. Without thoughtful design, proactive systems risk being perceived as intrusive by human users. We address the issue by establishing a new taxonomy concerning three key dimensions of human-centered PCAs, namely Intelligence, Adaptivity, and Civility. We discuss potential research opportunities and challenges based on this new taxonomy upon the five stages of PCA system construction. This perspectives paper lays a foundation for the emerging area of conversational information retrieval research and paves the way towards advancing human-centered proactive conversational systems.