The primary objective of this research is to develop new, cognitively informed computational models of the generation of narrative that is told within three-dimensional virtual environments. Motivated by theoretic models of narrative structure and psychological models of narrative comprehension, techniques will be developed for creating accounts of sequences of events and the techniques needed to convey them to users. These techniques will use these models to search for narratives that are at once coherent and effective at communicating the underlying event structure. The project will explore how computational models of the mental processes performed by people when experiencing film or machinima can inform an automatic process used to generate the films themselves. Extensive empirical studies will provide a comprehensive evaluation of the effectiveness of the models.

The research program has three major thrusts: (1) Integrating generative models of character plans with narrative theoretic structural models to create storylines that reflect both rich character goal structures and recognizable narrative elements. (2) Developing methods for shot sequence selection that build on pragmatic models from linguistic communication to effectively convey characters' plans and goals. (3) Developing and then evaluating a system that integrates these parts to search for narratives that are both coherent and effective.

The project will contribute to the infrastructure of science and education by training new researchers (graduate research assistants) in an area that is broadly multidisciplinary (computer science, cognitive science and psychology). These new researchers will gain from the project a unique integrated view of the contributing disciplines. Team members will participate in the dissemination of results through journal articles and presentations at national and international conferences on creativity, artificial intelligence, human-computer interaction and psychology. It is expected that the work will have a significant impact on the theory and understanding of creativity, particularly in the context of narrative, serving as a foundation for a new generation of tools that support the creative process.

Agency
National Science Foundation (NSF)
Institute
Division of Information and Intelligent Systems (IIS)
Application #
1319912
Program Officer
William Bainbridge
Project Start
Project End
Budget Start
2013-08-01
Budget End
2016-10-31
Support Year
Fiscal Year
2013
Total Cost
$352,696
Indirect Cost
Name
North Carolina State University Raleigh
Department
Type
DUNS #
City
Raleigh
State
NC
Country
United States
Zip Code
27695