NetworkING: using character relationships for interactive narrative generation

  • Authors:
  • Julie Porteous;Fred Charles;Marc Cavazza

  • Affiliations:
  • Teesside University, Middlesbrough, United Kingdom;Teesside University, Middlesbrough, United Kingdom;Teesside University, Middlesbrough, United Kingdom

  • Venue:
  • Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this work, we revisit the duality between character and plot in Interactive Storytelling, and demonstrate the important role of social relationships between virtual characters in the generation of narrative: an aspect that has hitherto been overlooked as a generation mechanism. We argue that the structure of social relationships between characters can be used as a powerful mechanism to determine a narrative, putting less emphasis on the details of plot structure. This enables character relationships in the network and the situations which naturally arise from character interactions to act as key drivers for narrative generation. The mechanism is fully implemented in a demonstration system which allows the exploration of the impact of changes in the social network on narrative diversity using a baseline set of narrative actions typical of the popular medical drama genre. Experimental results confirm our expectation that changes in the relationships between virtual agents in a social network can yield significant qualitative difference in system-generated narratives. This constitutes a new mechanism for narrative generation somehow closer to how modern dramas are shaped in specific genres, where situations and relationships are determinant.