A Plan-Based Personality Model for Story Characters
Alireza Shirvani, Stephen G. Ware · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · 2019
Believable virtual characters enhance the experience of interactive virtual worlds. BDI-based state-space narrative planners make their characters more compelling by granting them specific goals to pursue and different (possibly wrong) beliefs about the state of the world. However, such systems do not account for character individuality. We extend work on narrative planning by proposing a personality model based on the Big Five. This paper discusses how each factor of the Big Five is represented by narrative planning features. We also present a study to evaluate whether human readers can perceive the modeled personality traits through simple action patterns in short stories.