Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks

Abstract

Dialogue systems capable of social influence such as persuasion, negotiation, and therapy, are essential for extending the use of technology to numerous realistic scenarios. However, existing research primarily focuses on either task-oriented or open-domain scenarios, a categorization that has been inadequate for capturing influence skills systematically. There exists no formal definition or category for dialogue systems with these skills and data-driven efforts in this direction are highly limited. In this work, we formally define and introduce the category of social influence dialogue systems that influence users' cognitive and emotional responses, leading to changes in thoughts, opinions, and behaviors through natural conversations. We present a survey of various tasks, datasets, and methods, compiling the progress across seven diverse domains. We discuss the commonalities and differences between the examined systems, identify limitations, and recommend future directions. This study serves as a comprehensive reference for social influence dialogue systems to inspire more dedicated research and discussion in this emerging area.

Be Selfish, But Wisely: Investigating the Impact of Agent Personality in Mixed-Motive Human-Agent Interactions

“…As discussed in prior work (Chawla et al, 2023), our analysis reflects upon the multi-faceted nature of the notion of success in negotiations, where observing a single dimension can be misleading. For example, when interacting with model S, the M p=S r=selfish agent seems to get high points for itself.…”

“…Negotiation has been actively studied in diverse research areas, including Economics, Psychology, and Affective Computing (Carnevale and Pruitt, 2003). More recently, it has been studied as a social influence dialogue task for automated systems (Chawla et al, 2023). Automated systems capable of negotiating via realistic modes of communication, such as natural language, hold a huge potential in making social skills training more scalable and effective (Johnson et al, 2017).…”

“…"Firms [Agents], in the pursuit of profits, are led, as if by an invisible hand, to do what is best for the world." -Adam Smith: The Father of Modern Economics Negotiation is a crucial social influence interaction (Chawla et al, 2023), ubiquitous in everyday scenarios, from deciding who performs household chores to high-stakes business deals and legal proceedings. Consequently, negotiation dialogue systems find numerous applications in advancing conversational AI assistants (Leviathan and Matias, Table 1: A sample problematic negotiation dialogue between the standard RL agent (Alice) and a supervised model (Bob), based on Lewis et al (2017).…”