A Generative Model of Group Conversation

TL;DR

This paper introduces a generative computational model for group conversations among virtual agents, enabling more dynamic and believable NPC interactions in gaming environments by simulating multi-agent dialogue with personality and relationship influences.

Contribution

It presents a novel model for multi-agent group conversations that incorporates rules for turn-taking, belief and sentiment change, and emotional responses based on personality and context.

Findings

Character personalities influence speaking frequency.

Heterogeneous groups induce more belief change.

Model enables more realistic NPC interactions.

Abstract

Conversations with non-player characters (NPCs) in games are typically confined to dialogue between a human player and a virtual agent, where the conversation is initiated and controlled by the player. To create richer, more believable environments for players, we need conversational behavior to reflect initiative on the part of the NPCs, including conversations that include multiple NPCs who interact with one another as well as the player. We describe a generative computational model of group conversation between agents, an abstract simulation of discussion in a small group setting. We define conversational interactions in terms of rules for turn taking and interruption, as well as belief change, sentiment change, and emotional response, all of which are dependent on agent personality, context, and relationships. We evaluate our model using a parameterized expressive range analysis, observing correlations between simulation parameters and features of the resulting conversations. This analysis confirms, for example, that character personalities will predict how often they speak, and that heterogeneous groups of characters will generate more belief change.