Generation of Dilemma-Based Narratives: Method and Turing Test Evaluation

Heather Barber, Daniel Kudenko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes the analysis of the narrative generation aspect of the Generator of Adaptive Dilemma-based Interactive Narratives (GADIN). This system automatically generates narratives that are focused around dilemmas to create dramatic tension. The dilemmas are based on those cliches encountered in many of today's soap operas. A story planner creates sequences of actions that lead to dilemmas for storyworld characters. A narrative generated by GADIN is compared to that which took place in a television soap opera. The stories were subjected to a Turing-style test, with 127 participants, which showed that the readers could not determine which narrative had been written by a computer.

Original languageEnglish
Title of host publicationINTERACTIVE STORYTELLING, PROCEEDINGS
EditorsU Spierling, N Szilas
Place of PublicationBERLIN
PublisherSpringer
Pages214-217
Number of pages4
Volume5334 LNCS
ISBN (Print)978-3-540-89424-7
Publication statusPublished - 2008
Event1st Joint International Conference on Interactive Digital Storytelling (ICIDS 2008) - Erfurt
Duration: 26 Nov 200829 Nov 2008

Conference

Conference1st Joint International Conference on Interactive Digital Storytelling (ICIDS 2008)
CityErfurt
Period26/11/0829/11/08

Cite this