Felt: A Simple Story Sifter

Kreminski, Max; Dickinson, Melanie; Wardrip‐Fruin, Noah

doi:10.1007/978-3-030-33894-7_27

Cited by 20 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Szilas et al [47] discuss interestingness as a paradox dramatic situation with obstacles and conflicts, albeit applicable to stories as successive events. Yet, to approach subjective measurements such as interestingness, most research turns towards having human evaluation [48], [49] or using such to form human models to be used as surrogate models [50], [51].…”

Section: Related Workmentioning

confidence: 99%

TropeTwist: Trope-based Narrative Structure Generation

Álvarez¹,

Font²

2022

Preprint

View full text Add to dashboard Cite

Games are complex, multi-faceted systems that share common elements and underlying narratives, such as the conflict between a hero and a big bad enemy or pursuing some goal that requires overcoming challenges. However, identifying and describing these elements together is non-trivial as they might differ in certain properties and how players might encounter the narratives. Likewise, generating narratives also pose difficulties when encoding, interpreting, analyzing, and evaluating them. To address this, we present TropeTwist, a trope-based system that can describe narrative structures in games in a more abstract and generic level, allowing the definition of games' narrative structures and their generation using interconnected tropes, called narrative graphs. To demonstrate the system, we represent the narrative structure of three different games. We use MAP-Elites to generate and evaluate novel qualitydiverse narrative graphs encoded as graph grammars, using these three hand-made narrative structures as targets. Both handmade and generated narrative graphs are evaluated based on their coherence and interestingness, which are improved through evolution.

show abstract

Section: Related Workmentioning

confidence: 99%

TropeTwist: Trope-based Narrative Structure Generation

Álvarez¹,

Font²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…WAWLT is built around story sifting [22,23] in both its implementation and its design, making central use of the story sifting and simulation engine Felt [11]. Story sifting approaches to emergent narrative attempt to address the challenges of narrative generation through curation: by allowing a simulated storyworld to run, generating a massive chronicle of mostly-uninteresting simulated events, and then searching within this chronicle for patterns of narratively compelling events, it is possible to provide players with compelling stories or microstories without baking knowledge of how to tell a compelling story directly into the simulation engine itself.…”

Section: Related Workmentioning

confidence: 99%

“…The state of the WAWLT storyworld is stored in a DataScript [18] database managed by the Felt [11] story sifting and simulation engine. Storyworld entities represented in the database include characters, projects, institutions, events, relationships, and impressions.…”

Section: Architecture 41 Storyworld State Databasementioning

confidence: 99%

See 1 more Smart Citation

Why Are We Like This?: The AI Architecture of a Co-Creative Storytelling Game

Kreminski

Dickinson

Mateas

et al. 2020

International Conference on the Foundations of Digital Games

Self Cite

View full text Add to dashboard Cite

We present Why Are We Like This? (WAWLT), a mixed-initiative, co-creative storytelling game in which two players develop a story transcript by selecting and editing actions to perform and narrativize in an ongoing simulation. In this paper, we lay out the major technical features of WAWLT 's AI architecture-including story sifting via Datalog queries, social simulation, action suggestions, and player-specified but system-understandable author goals-and discuss how these features work together to produce a play experience that facilitates player creativity. CCS CONCEPTS • Software and its engineering → Interactive games; • Applied computing → Computer games.

show abstract

“…It selects stories from among the simulation traces by identifying the ones that score highest on certain story-coherence metrics. Felt (Kreminski, Dickinson, and Wardrip-Fruin 2019) also extracts stories from simulations, but with an emphasis on finding subsets of one large simulation. It maintains a database of events from a story world and provides a query language for "sifting" the world history to find event patterns that match a desired story structure.…”

Section: Related Workmentioning

confidence: 99%

A Good Story Is One in a Million: Solution Density in Narrative Generation Problems

Siler

Ware

2020

AIIDE

View full text Add to dashboard Cite

Narrative generation systems can be classified on a spectrum from strong autonomy to strong story. Systems on the strong autonomy side treat characters as fully independent agents but may struggle to meet the author’s requirements, while those on the strong story side direct character behaviors centrally but may struggle to create the illusion of character believability. In this paper, we use benchmark story generation problems as a framework to compare the spaces of stories that could be generated by prototypical strong story and strong autonomy systems. Comparing the relative solution densities of these spaces helps us quantify how common certain desirable narrative properties are. This can be informative for system designers when deciding, for instance, whether to strictly enforce all desired properties or to generate and filter from a broader class of solutions.

show abstract

Felt: A Simple Story Sifter

Cited by 20 publications

References 19 publications

TropeTwist: Trope-based Narrative Structure Generation

TropeTwist: Trope-based Narrative Structure Generation

Why Are We Like This?: The AI Architecture of a Co-Creative Storytelling Game

A Good Story Is One in a Million: Solution Density in Narrative Generation Problems

Contact Info

Product

Resources

About