Validating a plan-based model of narrative conflict

Glaive is a state-space planner based on Hoffmann and Nebel's Fast-Forward which solves the narrative planning problem defined by Riedl and Young — to construct a plan which achieves the author's goals out of steps which are clearly motivated and goal-oriented toward individual character goals. Glaive reasons about how characters cooperate and conflict based on causal structures and possible worlds. By leveraging the unique constraints of narrative planning, Glaive reduces its branching factor and calculates a more accurate heuristic. We evaluate it on 8 narrative planning problems and demonstrate that it can solve certain non-trivial problems in under 1 second.

show abstract

“…2. Fantasy (80 / 46 / 0 / 6), from Ware and Young (2012) Niehaus (2009). Table 1 gives Glaive's performance on these problems.…”

Section: Discussionmentioning

confidence: 99%

Glaive: A State-Space Narrative Planner Supporting Intentionality and Conflict

Ware

Young

2021

AIIDE

View full text Add to dashboard Cite

show abstract

“…Examples include early systems such as TALE-SPIN (Meehan 1977), MINSTREL (Turner 1993;Tearse et al 2014), and UNIVERSE (Lebowitz 1983). More recent systems, such as FABULIST (Riedl and Young 2010), have adopted more powerful planning formalisms and imported concepts from narratology, or sought to extend the planning process to encode different notions of story quality (Porteous and Cavazza 2009;Ware and Young 2011).…”

Section: Related Workmentioning

confidence: 99%

“…Another strand in story generators involves the development of explicit cognitive models, such as in MEXICA (Pérez y Pérez and Sharples 2001), or the design of generators influenced by models of narrative comprehension from cognitive science (Ware et al 2014;Ware and Young 2012).…”

Section: Related Workmentioning

confidence: 99%

Dear Leader’s Happy Story Time: A Party Game Based on Automated Story Generation

Horswill

2021

AIIDE

View full text Add to dashboard Cite

Players in Dear Leader’s Happy Story Time are placed in the role of contestants in a reality TV show where they are forced to audition for roles in the upcoming film of the host, a deranged billionaire who has inexplicably been elected president. The stories are produced by a story generator that combines stock plots and characters to produce kitsch story outlines. The players then collaborate to improvise a camp performance of the outline. The game design provides a context for experimenting with automatic story generation within a narrative game, as well as an opportunity for experimenting with knowledge representation schemes for expressing the tropes of popular narrative. The story generator uses a higher-order logic for describing tropes, and an HTN planning algorithm based on Nau et al.’s SHOP.

show abstract

“…The first experiment evaluates the plan-based structure of CPOCL, along with the three dimensions that can be directly observed in a CPOCL plan: participants, reason, and duration [39]. Human subjects were given three short stories and asked to list all the conflicts they observed.…”

Section: B Design Of the First Experimentsmentioning

confidence: 99%

A Computational Model of Plan-Based Narrative Conflict at the Fabula Level

Ware

Young

Harrison

et al. 2014

IEEE Trans. Comput. Intell. AI Games

Self Cite

View full text Add to dashboard Cite

Conflict is an essential element of interesting stories. In this paper, we operationalize a narratological definition of conflict and extend established narrative planning techniques to incorporate this definition. The conflict partial order causal link planning algorithm (CPOCL) allows narrative conflict to arise in a plan while maintaining causal soundness and character believability. We also define seven dimensions of conflict in terms of this algorithm's knowledge representation. The first three-participants, reason, and duration-are discrete values which answer the "who?" "why?" and "when?" questions, respectively. The last four-balance, directness, stakes, and resolution-are continuous values which describe important narrative properties that can be used to select conflicts based on the author's purpose. We also present the results of two empirical studies which validate our operationalizations of these narrative phenomena. Finally, we demonstrate the different kinds of stories which CPOCL can produce based on constraints on the seven dimensions.

show abstract

Validating a plan-based model of narrative conflict

Cited by 12 publications

References 11 publications

Glaive: A State-Space Narrative Planner Supporting Intentionality and Conflict

Glaive: A State-Space Narrative Planner Supporting Intentionality and Conflict

Dear Leader’s Happy Story Time: A Party Game Based on Automated Story Generation

A Computational Model of Plan-Based Narrative Conflict at the Fabula Level

Contact Info

Product

Resources

About