A Goal-Based Model of Personality for Planning-Based Narrative Generation

Characters that are capable of expressing emotions seem more lifelike to a human audience. Interacting with emotional characters may cause a human user to feel empathy and to care for their fate. In turn, the audience may feel more engaged in the story. We take a step to address the lack of computational models of emotions for strong-story systems and propose to extend strong-story state-space narrative planners, already equipped with intentionality and belief, to reason about character emotions. Our proposed system is multi-agent, highly domain-independent, and focused on reasoning and decision making. In this paper, we evaluate to what extent our system can accurately model a set of emotions and in doing so, improve the believability of story characters.

Section: Discussionmentioning

confidence: 99%

A Formalization of Emotional Planning for Strong-Story Systems

Shirvani

Ware

2020

“…Extending IPOCL, Ware and Young's (Ware and Young 2011) CPOCL adds a representation of conflict in story plans where one character might take actions that interfere with or thwart the execution of actions taken by other characters. In the Mask planning system, Bahamón and his collaborators (Bahamón, Barot, and Young 2015;Bahamón and Young 2017) incorporate a model of character personality that is used to drive character choice for action that expresses character personality traits.…”

Section: Related Workmentioning

confidence: 99%

“…One of the strengths of recent planning-based narrative generation methods (e.g. (Young et al 2013;Porteous and Cavazza 2009;Coman and Munoz-Avila 2012;Bahamón, Barot, and Young 2015;Teutenberg and Porteous 2013)) is that they retain many of the benefits of classical planning while also increasing the expressive Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.…”

Section: Introductionmentioning

confidence: 99%

HeadSpace: Incorporating Action Failure and Character Beliefs into Narrative Planning

Sanghrajka

Young

Thorne

2022

Previous work on story planning has lacked a knowledge representation for characters that attempt actions that fail because of the characters' misconceptions about the world state. This work describes HeadSpace, a state-space heuristic search planning system that generates stories that track and manipulate characters' beliefs about the story world. The planner produces story plans with actions that are attempted but fail. We show an example story plan that contains failed-action content that cannot be generated by typical planning-based approaches to story creation, and we provide an analytical evaluation that characterizes our planner's increased expressive range relative to other narrative planners addressing character belief and/or failed action execution.

“…Much work that has gone into plan-based story generation (e.g. (Ware et al 2014;Bahamón, Barot, and Young 2015;Teutenberg and Porteous 2013)) has sought to retain as many of the benefits of classical planning as possible while also increasing the expressive range of narrative generators.…”

Section: Introductionmentioning

confidence: 99%

Generating Stories that Include Failed Actions by Modeling False Character Beliefs

Thorne

Young

2021

Previous work on story planning has lacked a knowledge representation for characters that make mistakes in the execution of their actions. In particular, characters' execution mistakes that arise from errors in belief have not been modeled. In this paper, we describe a state-space planning system and its belief model, together called HeadSpace, that generates stories that track and manipulates characters' belief about the story world around them. This model is used to produce actions in stories that are attempted but that fail. We show an example story plan that contains failed-action content that cannot be generated by typical planning-based approaches to story creation.