Narrative Planning: Balancing Plot and Character

Abstract

Narrative, and in particular storytelling, is an important part of the human experience. Consequently, computational systems that can reason about narrative can be more effective communicators, entertainers, educators, and trainers. One of the central challenges in computational narrative reasoning is narrative generation, the automated creation of meaningful event sequences. There are many factors -logical and aesthetic -that contribute to the success of a narrative artifact. Central to this success is its understandability. We argue that the following two attributes of narratives are universal: (a) the logical causal progression of plot, and (b) character believability. Character believability is the perception by the audience that the actions performed by characters do not negatively impact the audience's suspension of disbelief. Specifically, characters must be perceived by the audience to be intentional agents. In this article, we explore the use of refinement search as a technique for solving the narrative generation problem -to find a sound and believable sequence of character actions that transforms an initial world state into a world state in which goal propositions hold. We describe a novel refinement search planning algorithmthe Intent-based Partial Order Causal Link (IPOCL) planner -that, in addition to creating causally sound plot progression, reasons about character intentionality by identifying possible character goals that explain their actions and creating plan structures that explain why those characters commit to their goals. We present the results of an empirical evaluation that demonstrates that narrative plans generated by the IPOCL algorithm support audience comprehension of character intentions better than plans generated by conventional partial-order planners.

LifeLogging: Personal Big Data

“…have suggested that narrative text should be generated to represent each lifelog unit. As described by Riedl and Young (2010), "narrative is a sequence of events that describes how the story world change over time", and we know that narratives can be used to support keyword text searches using information retrieval techniques from Jaimes et al (2004). After all, text is the natural method that users now have to locate knowledge using web search engines.…”

Thinning the Fourth Wall with Intelligent Prompt

“…With the exception of the systems mentioned above (see also [21]), most interactive storytelling systems do not directly address the emotional engagement of the audience. Rather, the research in interactive story generation tends to focus on the consistency of the plot in terms of characters' intentions and actions (see for example [13]). A notable exception is given by the use of player modeling to affect the emotional response of the users in [14].…”

Predicting User Choices in Interactive Narratives Using Indexter’s Pairwise Event Salience Hypothesis

“…Narrative planning (Riedl & Young, 2010) is an application of planning in which the domain is a story world, the goal is the author's goal for the end state of the story, and the operators represent possible story events. For example, the domain might define an operator attack (?attacker*, ?victim, ?location).…”