Brian O'Neill

A knowledge-based framework for the collaborative improvisation of scene introductions

This article describes a framework for the mixed-initiative collaborative creation of introductions to improvised theatrical scenes. This framework is based on the empirical study of experienced improvisational actors and the processes they use to reach shared understanding while creating the scene. Improvisation is a notable creative act, where the process of creating the scene is as much a product as the scene itself. Our framework models the processes of narrative scene establishment. It is designed to allow for the collaborative co-creation of the narrative by both human and computational improvisers. This mixed-initiative approach allows either type of improviser (AI or human) to deal with the ambiguities that are inherent to improvisational theatre. This emphasis on equal collaborative creation also differentiates this framework from existing work in story generation and interactive narrative.

Creativity support for novice digital filmmaking

Machinima is a new form of creative digital filmmaking that leverages the real time graphics rendering of computer game engines. Because of the low barrier to entry, machinima has become a popular creative medium for hobbyists and novices while still retaining borrowed conventions from professional filmmaking. Can novice machinima creators benefit from creativity support tools? A preliminary study shows novices generally have difficulty adhering to cinematographic conventions. We identify and document four cinematic conventions novices typically violate. We report on a Wizard-of-Oz study showing a rule-based intelligent system that can reduce the frequency of errors that novices make by providing information about rule violations without prescribing solutions. We discuss the role of error reduction in creativity support tools.

Distributed creative cognition in digital filmmaking

This paper reports on an empirical study that uses a Grounded Theory approach to investigate the creative practices of Machinima filmmakers. Machinima is a new digital film production technique that uses the 3D graphics and real time rendering capability of video game engines to create films. In contrast to practices used in traditional film production, weve found that Machinima filmmakers explore and evaluate ideas in real time. These filmmakers generate vague and underspecified mental images, which are then explored and refined using the real time rendering capabilities of game engines. The game engine assists the filmmaker to fill in indeterminate details, which allows creative exploration of scenes through playfully experimenting with parameters such as camera angle and position, lighting, and character position. Creative exploration distributes the cognitive task of evaluation between the human user and the Machinima tool to enable evaluation through exploring possible scene configurations.

Toward a computational framework of suspense and dramatic arc

We propose a computational framework for the recognition of suspense and dramatic arc in stories. Suspense is an affective response to narrative structure that accompanies the reduction in quantity or quality of plans available to a protagonist faced with potential goal failure and/or harm. Our work is motivated by the recognition that computational systems are historically unable to reliably reason about aesthetic or affective qualities of story structures. Our proposed framework, Dramatis, reads a story, identifies potential failures in the plans and goals of the protagonist, and computes a suspense rating at various points in the story. To compute suspense, Dramatis searches for ways in which the protagonist can overcome the failure and produces a rating inversely proportional to the likelihood of the best approach to overcoming the failure. If applied to story generation, Dramatis could allow for the creation of stories with knowledge of suspense and dramatic arc.

Towards intelligent authoring tools for machinima creation

As user-created content increasingly becomes an ever more prominent element of modern game design, tools have been developed to aide in the creative process for several forms of digital media, including machinima. Because creating content that will be valued by the community is a challenging process, tools are needed that will assist novices in both technical realization and optimization of content. We are exploring tools for machinima authoring that use a 3-pronged approach: authoring via metaphor, performance, and automation. Future work involves using AI to provide feedback to machinima authors, suggesting sensible attributes for scenes based on prior input by acting as a surrogate audience.

Supporting human creative story authoring with asynthetic audience

Human creativity plays an important role in the production of many of the media products that permeate our society. However, non-expert creators are often limited by a lack of technical ability, as opposed to creative ability. This is especially true for story authoring. We present an approach to supporting creativity using synthetic audience - an intelligent agent that acts as (a) a surrogate story recipient and (b) critic capable of providing constructive feedback. We describe initial efforts based on computational modeling of cognitive processes and creativity.

Applying Qualitative Research Methods to Narrative Knowledge Engineering

We propose a methodology for knowledge engineering for narrative intelligence systems, based on techniques used to elicit themes in qualitative methods research. Our methodology uses coding techniques to identify actions in natural language corpora, and uses these actions to create planning operators and procedural knowledge, such as scripts. In an iterative process, coders create a taxonomy of codes relevant to the corpus, and apply those codes to each element of that corpus. These codes can then be combined into operators or other narrative knowledge structures. We also describe the use of this methodology in the context of Dramatis, a narrative intelligence system that required STRIPS operators and scripts in order to calculate human suspense responses to stories.

Toward a computational model of affective responses to stories for augmenting narrative generation

Current approaches to story generation do not utilize models of human affect to create stories with dramatic arc, suspense, and surprise. This paper describes current and future work towards computational models of affective responses to stories for the purpose of augmenting computational story generators. I propose two cognitively plausible models of suspense and surprise responses to stories. I also propose methods for evaluating these models by comparing them to actual human responses to stories. Finally, I propose the implementation of these models as a heuristic in a search-based story generation system. By using these models as a heuristic, the story generation system will favor stories that are more likely to produce affective responses from human readers.

Making a scene: people and artificial intelligence improvising together

How can people and AI equally participate in creating something? How do they do it when they cannot edit or revise their work?