CS 7634 / 4803 SVW / LCC 8803 MR : A.I. Storytelling in Virtual Worlds
All papers are available in T-Square
(The list is not yet complete)
Mobile Alternate Reality Games
[MacVean11] Andrew MacVean, Sanjeet Hajarnis, Brandon Headrick, Aziel Ferguson, Chinmay Barve, Devika Karnik, and Mark O. Riedl. WeQuest: Scalable Alternate Reality Games Through End-User Content Authoring. To appear in the proceedings of the 8th ACM Conference on Advances in Computer Entertainment (ACE), 2011.
Alternate Reality Games (ARGs) are interactive narrative experiences that engage the player by layering a fictional world over the real world. ARG stories are often geo-specific, requiring players to visit specific locations in the world. Con- sequently, ARGs are played infrequently and only by those who live within proximity of the locations that the stories reference. In this paper, we describe an ARG platform, We- Quest, that addresses the geo-specificity limitation through end-user content generation. An authoring tool allows end- users to create new ARG stories that can be executed auto- matically on geo-location aware mobile devices, leading to greater numbers of available stories to be played. An artifi- cial intelligence processed called location translation makes geo-specific ARGs playable anywhere in the world.
[Riedl11] Mark Riedl, Boyang Li, Hua Ai, and Ashwin Ram. Robust and Authorable Multiplayer Interactive Narrative Experiences. To appear in the proceedings of the 7th ACM Converence on Aritificial Intelligence and Interactive Digital Entertainment, 2011.
Interactive narrative systems attempt to tell stories to
players capable of changing the direction and/or outcome of the story. Despite the growing importance of
multiplayer social experiences in games, little research
has focused on multiplayer interactive narrative experiences. We performed a preliminary study to determine how human directors design and execute multiplayer interactive story experiences in online and real
world environments. Based on our observations, we developed the Multiplayer Storytelling Engine that manages a story world at the individual and group levels
Our ﬂexible story representation enables human authors
to naturally model multiplayer narrative experiences.
An intelligent execution algorithm detects when the author’s story representation fails to account for player behaviors and automatically generates a branch to restore
the story to the authors’ original intent, thus balancing
authorability against robust multiplayer execution.
[Reed11] Aaron Reed, Ben Samuel, Anne Sullivan, Ricky Grant, April Grow, Justin Lazaro, Jennifer Mahal, Sri Kurniawan, Marilyn Walker, and Noah Wardrip-Fruin. A Step Towards the Future of Role-Playing Games: The SpyFeet Mobile RPG Project. To appear in the proceedings of the 7th Annual Conference on Artificial Intelligence and Interactive Digital Entertainment, 2011.
Meaningful choice has often been identified as a key
component in a player’s engagement with an interac-
tive narrative, but branching stories require tremendous
amounts of hand-authored content, in amounts that in-
crease exponentially rather than linearly as more choice
points are added. Previous approaches to reducing au-
thorial burden for computer RPGs have relied on cre-
ating better tools to manage existing unwieldy struc-
tures of quests and dialogue trees. We hypothesize that
reducing authorial burden and increasing agency are
two sides of the same coin, requiring specific advance-
ments in two related areas of design and technology
research: (1) dynamic story management architecture
that represents story events abstractly and allows story
elements to be selected and re-ordered in response to
player choices, and (2) dynamic dialogue generation to
allow a single story event to be revealed differently by
different characters and in the context of dynamic rela-
tionships between those characters and the player. This
paper describes SpyFeet, a playable prototype of a sto-
rytelling system designed to test this hypothesis.
[Lim07] M. Y. Lim and R. Aylett. Narrative construction in a mobile tour guide. In Proceedings of the 4th International Conference on Virtual Storytelling, 2007.
Storytelling capabilities are vital aspect of a tour guide. In
this paper, we present a mobile tour guide that emulates a real guide's
behaviour by presenting stories based on the user's interests, its own
interests, its belief and its current memory activation. This research
moves away from the concept of a guide that recites facts about places
or events towards a guide that utilises improvisational storytelling tech-
niques. Contrasting views and personality are achieved with an inclusion
of emotional memories containing the guide's ideology and its past ex-
[Stock07] O. Stock, M. Zancanaro, P. Busetta, C. Callaway, A. Kruger, M. Kruppa, T. Kuik, E. Not, and C. Rocchi. Adaptive, intelligent presentation of information for the museum visitor in PEACH. User Modeling and User-Adapted Interaction, 17(3):257-304, 2007.
The study of intelligent user interfaces and user modeling and adaptation is well
suited for augmenting educational visits to museums. We have defined a novel integrated
framework for museum visits and claim that such a framework is essential in such a vast
domain that inherently implies complex interactivity. We found that it requires a significant
investment in software and hardware infrastructure, design and implementation of intelligent
interfaces, and a systematic and iterative evaluation of the design and functionality of user
interfaces, involving actual visitors at every stage. We defined and built a suite of interactive
and user-adaptive technologies for museum visitors, which was then evaluated at the
Buonconsiglio Castle in Trento, Italy: (1) animated agents that help motivate visitors and
focus their attention when necessary, (2) automatically generated, adaptive video documentaries
on mobile devices, and (3) automatically generated post-visit summaries that reflect
the individual interests of visitors as determined by their behavior and choices during their
visit. These components are supported by underlying user modeling and inference mechanisms
that allow for adaptivity and personalization. Novel software infrastructure allows for
agent connectivity and fusion of multiple positioning data streams in the museum space.We
conducted several experiments, focusing on various aspects of PEACH.
[gustafsson06] Anton Gustafsson, John Bichard, Liselott Brunnberg, Oskar Juhlin, Marco Combetto. Believable environments – Generating interactive storytel-ling in vast location-based pervasive games. Proceedings of the 2006 ACM Conference on Advances in Computer Entertainment, 2006.
Generating content into vast areas is a relevant challenge in the field of location-based pervasive games. In this paper, we present a game proto-type that enables children travelling in the back seat of a car to enjoy a narrated experience where gameplay combines with the experience of trav-eling through the road network. The prototype is designed to provide what we refer to as a believ-able environment. We propose four design char-acteristics to persuasively include a journey within a pervasive game. First, the story should refer to geographical objects with their everyday meanings. Second, the game’s scale needs to cover vast areas. Third, the application should provide sequential storytelling to make it fit with the journey experience, and finally it should pro-vide interaction support where players can en-gage in gameplay and interact with the computer in various ways at the same time as they are looking out of the car window. We describe how these requirements have been implemented in the prototype and present an initial performance test.
[Bruckman90] Bruckman. 1990. The Combinatorics of Storytelling: Mystery Train Interactive. Unpublished Manuscript.
[Thue07] David Thue, Vadim Bulitko, Marcia Spetch, and Eric Wasylishen. Interactive Storytelling: A Player Modelling Approach. The Third Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE).
In recent years, the fields of Interactive Storytelling and
Player Modelling have independently enjoyed increased interest
in both academia and the computer games industry. The
combination of these technologies, however, remains largely
unexplored. In this paper, we present PaSSAGE (Player-
Specific Stories via Automatically Generated Events), an interactive
storytelling system that uses player modelling to automatically
learn a model of the player’s preferred style of
play, and then uses that model to dynamically select the content
of an interactive story. Results from a user study evaluating
the entertainment value of adaptive stories created by
our system as well as two fixed, pre-authored stories indicate
that automatically adapting a story based on learned player
preferences can increase the enjoyment of playing a computer
role-playing game for certain types of players.
[Sharma07] Manu Sharma, Manish Mehta, Santiago Ontanon, and Ashwin Ram. (2007). Player Modeling Evaluation for Interactive Fiction. Third Artificial Intelligence for Interactive Digital Entertainment Conference (AIIDE-07), Workshop on Optimizing Player Satisfaction
A growing research community is working towards employing
drama management components in story-based
games that guide the story towards specific narrative
arcs depending on a particular player’s playing patterns.
Intuitively, player modeling should be a key component
for Drama Manager (DM) based approaches to succeed
with human players. In this paper, we report a
particular implementation of the DM component connected
to an interactive story game, Anchorhead, while
specifically focusing on the player modeling component.
We analyze results from our evaluation study and
show that similarity in the trace of DM decisions in previous
games can be used to predict interestingness of
game events for the current player. Results from our
current analysis indicate that the average time spent in
performing player actions provides a strong distinction
between players with varying degrees of gaming experience,
thereby helping the DM to adapt its strategy based
on this information.
[Nelson05] Nelson, M. and Mateas, M. (2005). Search-based drama management in the interactive fiction Anchorhead . Proceedings of the First Conference on Artificial Intelligence and Interactive Digital Entertainment.
Drama managers guide a user through a story experience by modifying the experience in reaction to the user's actions. Search-based drama management (SBDM) casts the dramamanagement problem as a search problem: Given a set of plot points, a set of actions the drama manager can take, and an evaluation of story quality, search can be used to optimize the user's experience. SBDM was first investigated by Peter Weyhrauch in 1997, but little explored since. We return to SBDM to investigate algorithmic and authorship issues, including the extension of SBDM to different kinds of stories, especially stories with subplots and multiple endings, and issues of scalability. In this paper we report on experiments applying SBDM to an abstract story search space based on the text-based interactive fiction Anchorhead. We describe the features employed by the story evaluation function, investigate design issues in the selection of a set of drama management actions, and report results for drama managed versus unmanaged stories for a simulated random user.
[Mateas02] Mateas, M. and Stern, A (2002). Architecture, authorial idioms and early observations of the interactive drama Facade. Technical report CMU-CS-02-198, School of Computer Science, Carnegie Mellon University.
Facade is an artificial intelligence-based art/research experiment in electronic narrative - an attempt to move beyond traditional branching or hyper-linked narrative to create a fully-realized, one-act interactive drama. Integrating an interdisciplinary set of artistic practices and artificial intelligence technologies, we are completing a three year collaboration to engineer a novel architecture for supporting emotional, interactive character behavior and drama-managed plot. Within this architecture we are building a dramatically interesting, real-time 3D virtual world inhabited by computer-controlled characters, in which the user experiences a story from a first-person perspective. Facade will be publicly released as a free download in 2003.
[Cavazza02] Cavazza, M., Charles, F., and Mead, S. (2002). Planning Characters' Behaviour in Interactive Storytelling. Journal of Visualization and Computer Animation, 13, 121-131.
In this paper, we describe a method for implementing the behaviour of artificial actors in the context of interactive storytelling. We have developed a fully implemented prototype based on the Unreal Tournament game engine, and carried experiments with a simple sitcom-like scenario. We discuss the central role of artificial actors in interactive storytelling and how real-time generation of their behaviour participates in the creation of a dynamic storyline. We follow previous work describing the behaviour of artificial actors through AI planning formalisms, and adapt it to the context of narrative representation. In this context, the narrative equivalent of a character's behaviour consists in its role. The set of possible roles for a given actor is represented as a Hierarchical Task Network (HTN). The system uses HTN planning to dynamically generate the character roles, by interleaving planning and execution, which supports dynamic interaction between actors, as well as user intervention in the unfolding plot. Finally, we present several examples of short plots and situations generated by the system from the dynamic interaction of artificial actors.
[Magerko04] Magerko, B. and Laird, J.E. Mediating the Tension Between Plot and Interaction. AAAI Workshop Series: Challenges in Game Artificial Intelligence, 2004.
When building a story-intensive game, there is always the
question of how much freedom to give the player. Give the
player too little, and he may feel constrained and
disconnected from the character he is controlling. Give him
too much freedom, and the progression of the story may lag
or stop altogether. This paper focuses on our attempt to
find a balance between offering the player a high degree of
interaction and providing a story-based experience where the
player is a key character. Our approach is embedded in our
Interactive Drama Architecture (IDA), which includes an
omniscient story director agent who manages the player’s
narrative experience. The director agent uses a declarative
description of the plot to track the player’s progress, detect
deviations from the plot, and make directions to supporting
characters in the game. Our director is embedded within a
game we have developed, called Haunt 2, which is an
extension to the Unreal Tournament engine.
[Riedl08] Mark O. Riedl, Andrew Stern, Don Dini, and Jason Alderman. Dynamic Experience Management in Virtual Worlds for Entertainment, Education, and Training. International Transactions on Systems Science and Applications, Special Issue on Agent Based Systems for Human Learning, vol. 4(2), 2008.
Modern computer systems have the ability to make
the storytelling experience interactive by involving a
participant or learner as a character in the narrative itself. We
present a framework for creating interactive narratives for
entertainment, educational, and training purposes based on a
type of agent called an experience manager. An experience
manager (a generalization of a drama manager) is an
intelligent computer agent that manipulates a virtual world to
coerce a participant’s experience to conform to a set of
provided properties. Our realization of the experience
manager automatically generates narrative content in order to
adapt to the user’s actions in the virtual world. The
experience management framework has been used to develop
an interactive version of Little Red Riding Hood and an
interactive practice environment called IN-TALE for
educating and training cognitive skills such as situation
awareness, cultural awareness, leadership, and decisionmaking.
Quest Generation in Games
[Hullett09] Kenneth Hullett and Michael Mateas. Scenario Generation for Emergency Rescue Training Games. In Proceedings of the Fourth International Conference on the Foundations of Digital Games (FDG 2009).
This paper presents a reliable and efficient approach to pro-
cedurally generating level maps based on the self-organization
capabilities of cellular automata (CA). A simple CA-based
algorithm is evaluated on an innite cave game, generating
playable and well-designed tunnel-based maps. The algo-
rithm has very low computational cost, permitting realtime
content generation, and the proposed map representation
exibility with respect to level design.
[Ashmore07] Calvin Ashmore and Michael Nitsche. 2007. The Quest in a Generated World. Proceedings of DiGRA 2007 Conference.
As procedural content becomes a more appealing option for
game development, procedurally determined context is
necessary to structure and make sense of this content. We
find that a useful means to structure content in 3D games is
the quest. The task of generating necessary context then
becomes one of quest generation. This paper describes how
we implemented a basic quest generator based on key and
lock puzzles into a procedural game world. It uses notion of
quest as spatial progression and discusses the design of the
game world and how our quest generator connects to it. Its
findings are twofold: on the technical level we managed to
implement a highly flexible content and context generator
into an existing game engine; one the content level we can
trace signs for higher player interest in quest-enhanced
procedural game worlds in comparison to unstructured
[Dormans10] Joris Dormans. (2010). Adventures in level design: generating missions and spaces for action adventure games. Proceedings of the FDG 2010 Workshop on Procedural Content Generation in Games.
This paper investigates strategies to generate levels for action adventure games. This genre relies more strongly on well-designed levels than rule-driven genres such as strategy or roleplaying games for which procedural level generation has been successful in the past. The approach outlined by this paper distinguishes between missions and spaces as two separate structures that need to be generated in two individual steps. It discusses the merits of different types of generative grammars for each individual step in the process.
[Li10] Boyang Li and Mark O. Riedl. An Offline Planning Approach to Game Plotline Adaptation. Proceedings of the 6th Conference on Artificial Intelligence for Interactive Digital Entertainment, Palo Alto, California, 2010.
Role-playing games, and other types of contemporary video
games, usually contain a main storyline consisting of several
causally related quests. As players have different motivations,
tastes and preferences, it can be beneficial to customize game
plotlines. In this paper, we present an offline algorithm for
adapting human-authored game plotlines for computer roleplaying
games to suit the unique needs of individual players,
thereby customizing gaming experiences and enhancing replayability.
Our approach uses an plan refinement technique
based on partial-order planning to (a) optimize the global
structure of the plotline according to input from a player model,
(b) maintain plotline coherence, and (c) facilitate authorial intent
by preserving as much of the original plotline as possible. A
theoretical analysis of the authorial leverage and a user study
suggest the benefits of this approach.
[Nitsche06] M. Nitsche, C. Ashmore, W. Hankinson, R. Fitzpatrick, J. Kelly, and K. Margenau. Designing Procedural Game Spaces: A Case Study. Proceedings of FuturePlay, 2006.
Procedural content generation holds many promises
for the design, art, and production of video games. It
also poses a number of challenges. This paper
concentrates on the procedural generation of game
spaces. We specifically argue for a connection of a
player’s agency with the procedural world
generation. First, space generation in games is
broken down into four main approaches: designercreated,
random, player-created, and procedural
spaces. Then, the paper introduces our experimental
game prototype Charbitat that merges these four
stages and provides a practical case study. Charbitat
generates game worlds based on the gaming style of
its players, who create the world as they play it. We
describe how the project met the challenges in
design and implementation. Finally, we point out
new questions opened up by the project and relevant
for procedural content generation.
[Pita07] Pita,, J., Magerko, B. and Brodie, S. TRUE STORY: Dynamically Generated, Contextually Linked Quests in Persistent Systems. FuturePlay, Toronto, ON, 2007.
Massively Multiplayer Online Role-Playing Games (MMORPGs)
typically use a handful of static conventions for involving players
in stories, such as predefined quest or story paths (a quest or story
path is one in which the user experiences a sequence of related
quests that must be accomplished in a particular order). Beyond
the work done in MMORPGs there has been strong research in
designing adaptive approaches to interactive fiction/drama that
dynamically author content for users of the interactions  .
The system architecture presented in this paper, TRUE STORY, is
designed to address issues concerning dynamically generated
quest or story paths in persistent worlds, such as MMORPGs, for
users to engage in more enhanced, interactive and personal
experiences. TRUE STORY empowers persistent world designers
by offering a truly modular approach for dynamically generating
and presenting compelling content that results in user experiences
worth telling a story about. The current implementation is set in a
game model to demonstrate a dynamic quest generation system
built to present users with unique and compelling experiences
linked by context to past quests and/or experiences. This is
achieved by utilizing history and relationships developed through
interaction between world objects and actions.
[Magerko06] Magerko, B., Stensrud, B., and Holt, L. Bringing the Schoolhouse Inside the Box – A Tool for Engaging, Individualized Training. 25th Army Science Conference, 2006. Orlando, FL.
The Interactive Storytelling Architecture for Training (ISAT) is designed to address the limitations of computer games for advanced distributed learning (ADL) and to fully realize the potential of games to become engaging and individualized training environments. The central component of the ISAT architecture is an intelligent director agent responsible for individualizing the training experience. To achieve this, the director tracks the trainee’s demonstration of knowledge and skills during the training experience. Using that information, the director plays a role similar to that of a schoolhouse trainer, customizing training scenarios to meet individual trainee needs. The director can react to trainee actions within a scenario, dynamically adapting the environment to the learning needs of trainee as well as the dramatic needs of the scene. This paper describes a prototype implementation of the ISAT architecture in the combat medic training domain, with an emphasis on the design of the director agent.
[Riedl10] Mark O. Riedl and R. Michael Young. (2010) Narrative Planning: Balancing Plot and Character. Journal of AI Research, 39.
The ability to generate narrative is of importance to computer systems that wish to use story effectively for entertainment, training, or education. We identify two properties of story – plot coherence and character believability – which play a role in the success of a story. Plot coherence is the perception by audience members that character actions have relevance to the outcome of the story. Character believability is the perception that character actions are motivated by agents' internal beliefs and desires. Unlike conventional planning in which plan goals represent an agent's intended world state, multiagent story planning involves goals that represent the outcome of a story. In order for the plans' actions to appear believable, multi-agent story planners must determine not only how agents' actions achieve a story's goal state, but must also ensure that each agent appears to be acting intentionally. We present a narrative generation planning system for multi-agent stories that is capable of generating narratives with both strong plot coherence and strong character believability. The planning algorithm uses causal reasoning and a simulated intention recognition process to drive plan creation.
[Gervas04] B Díaz-Agudo, P Gervás, F Peinado. (2004). A Case Based Reasoning Approach to Story Plot Generation. In Proc. of the 7 th European Conf. on Case Based Reasoning.
Automatic construction of story plots has always been a longed-for utopian dream in the entertainment industry, especially in the more commercial genres that are fueled by a large number of story plots with only a medium threshold on plot quality, such as TV series or video games. We propose a Knowledge Intensive CBR (KI-CBR) approach to the probem of generating story plots from a case base of existing stories analyzed in terms of Propp functions. A CBR process is defined to generate plots from a user gquery specifying an initial setting for the story, using an ontology to measure the semantical distance between words and structures taking part in the texts.
[Lebowitz84] Lebowitz, M. (1984). Creating characters in a story-telling universe. Poetics, 13, 171-194.
Extended story generation, i.e., the creation of continuing serials, presents difficult and interesting problems for Artificial Intelligence. We present here the first phase of the development of a program, UNIVERSE, that will ultimately tell extended stories. In particular, after descri inb our overall model of story telling, we present a method for creating universes of characters appropriate for extended story generation. This method concentrates on the need to keep story-telling unverses consistent and coherent. We also describe the information that must be maintained for characters and interpersonal relationships, and the use of stereotypical information about people to help motivate trait values. The use of historical events for motivation is also described. Finally, we present an example of a character generated by UNIVERSE.
[Lebowitz85] Lebowitz, M. (1985). Story-telling as planning and learning. Poetics, 14, 483-502.
The generation of extended plots for melodramatic fiction is an interesting task for Artificial Intelligece research, one that requires the application of genralization techniques to carry out fully. UNIVERSE is a story-telling program that uses plan-like units, 'plot fragments', to generate plot outlines. By using a rich library of plot fragments and a well-developed set of characters. UNIVERSE can create a wide range of plot outlines. In this paper we illustrate how UNIVERSE's plot gramgent library is used to create plot outlines and how it might be automatically extended using explanation-based generalization methods. Our methods are based on analysis of a television melodrama, including comparisons of similar stories.
[Meehan81] Meehan, J. (1981). Tale-Spin. In R.C. Schank and C.K. Riesbeck (Eds). Inside Computer Understanding (pp. 197-226). Lawrence Erlbaum Associates.
TALE-SPIN is a program that writes simple stories. It is easily distinguished from any of the "mechanical" devices one can use for writing stories, such as filling in slots in a canned frame. The goal behind the writing of TALE-SPIN was to find out what kinds of knowledge were needed in story generation. the writing of TALE-SPIN embodied the traditional AI cycle of research. Step 1 was to define a theory. Step 2 was to write a program modeling that theory and to add it to the existing system. Step 3 was to run the system and to observe where the model was incorrect or inadequate, thereby identifying the need for some more theory.
[Porteous09] Porteous, J. and Cavazza, M., 2009. Controlling Narrative Generation with Planning Trajectories: the Role of Constraints. International Conference on Interactive Digital Storytelling.
AI planning has featured in a number of Interactive Story-
telling prototypes: since narratives can be naturally modelled as a se-
quence of actions it has been possible to exploit state of the art plan-
ners in the task of narrative generation. However the characteristics of
a \good" plan, such as optimality, aren't necessarily the same as those
of a \good" narrative, where errors and convoluted sequences may oer
more reader interest, so some narrative structuring is required. In our
work we have looked at injecting narrative control into plan generation
through the use of PDDL3.0 state trajectory constraints which enable
us to express narrative control information within the planning repre-
sentation. As part of this we have developed an approach to planning
with such trajectory constraints. The approach decomposes the problem
into a set of smaller subproblems using the temporal orderings described
by the constraints and then solves these subproblems incrementally. In
this paper we outline our method and present results that illustrate the
potential of the approach.
[Swanson08] Reid Swanson and Andrew S. Gordon. Say anything: A massively collaborative open domain story writing companion. In First International Conference on Interactive Digital Storytelling, Erfurt, Germany, November 2008.
Interactive storytelling is an interesting cross-disciplinary area that
has importance in research as well as entertainment. In this paper we explore a
new area of interactive storytelling that blurs the line between traditional
interactive fiction and collaborative writing. We present a system where the
user and computer take turns in writing sentences of a fictional narrative.
Sentences contributed by the computer are selected from a collection of
millions of stories extracted from Internet weblogs. By leveraging the large
amounts of personal narrative content available on the web, we show that even
with a simple approach our system can produce compelling stories with our
[Perez01] Perez y Perez, R. and Sharples, M. (2001). MEXICA: a computer model of a cognitive account of creative writing. Journal of Experimental and Theoretical Artificial Intelligence, 13, 119-139.
MEXICA is a computer model that produces frameworks for short stories based on the engagement-refelction cognitive account of writing. During engagement MEXICA generates material guided by content and rhetorical constraints, avoiding the use of explicit goals or story-structure information. During reflection the system breaks impasses, evaluates the novelty and interestingness of the story in progress and verifies that coherence requirements are satisfied. In this way, MEXICA complements and extends those models of computerised story-telling based on traditional problem-solving techniques where explicit goals drive the generation of stories. This paper describes the engagement-reflection account of writing, the general characteristics of MEXICA and reports an evaluation of the program.
[Perez04] Pérez y Pérez, R. and Sharples, M. (2004) Three Computer-Based Models of Storytelling: BRUTUS, MINSTREL and MEXICA. Knowledge-Based Systems,17, 1, 15-29
This paper attempts to establish criteria to analyse and evaluate computer models of creativity in writing. The paper provides a brief review of the antecedents of automatic story-generation and offers a proposal for the analysis and evaluation of computer models of creativity in writing. It reviews three major projects to develop computer-based storywriters published between 1993 and 2000 and analyses their approach, similarities, differences and contributions. It compares the three approaches and discusses implications for the modelling of creativity in writing and the design of future story generation systems.
[Tearse10] Brandon Tearse, Michael Mateas, Noah Wardrip-Fruin. MINSTREL Remixed: A Rational Reconstruction. Proceedings of the Intelligent Narrative Technologies III Workshop, 2010.
In this paper, we introduce Minstrel Remixed, a rational reconstruction of MINSTREL by Scott Turner. In addition to
recreating the landmark story generation system for public usage
we also introduce a number of modifications that were made
during the reconstruction that allow for investigation into the
inner workings of the system. Additionally we introduce Minstrel
Remixed as a platform for use in Interactive Narrative
applications and provide a number of concrete examples.
[Tearse11] Brandon Tearse, Peter Mawhorter, Michael Mateas, NoahWardrip-Fruin. Experimental Results from a Rational Reconstruction of MINSTREL. Second International Conference on Computational Creativity, 2011.
This paper presents results from a rational reconstruction
project that is aimed at exploring the creative potential
of Scott Turner’s 1993 MINSTREL system. In particular,
we investigate the properties of Turner’s original system
of Transform-Recall-Adapt Methods (TRAMs) and analyze
the performance of an alternate TRAM application strategy.
In order to estimate the creativity of our reconstructed system
under various conditions, we measure both the variance
of the output space and the ratio of sensible to nonsensical
results (as determined by hand-labeling). Together, these
metrics give us insight into the creativity of the algorithm as
originally constructed, and allow us to measure the changes
that our modifications induce.
Virtual Character Agents
[Perlin96] Ken Perlin, Athomas Goldberg. 1996. Improv: a system for scripting interactive actors in virtual worlds. Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Improv is a system for the creation of real−time
behavior−based animated actors. There have been several
recent efforts to build network distributed autonomous agents.
But in general these efforts do not focus on the author’s view.
To create rich interactive worlds inhabited by believable
animated actors, authors need the proper tools. Improv
provides tools to create actors that respond to users and to
each other in real−time, with personalities and moods
consistent with the author’s goals and intentions.
Improv consists of two subsystems. The first
subsystem is an Animation Engine that uses procedural
techniques to enable authors to create layered, continuous,
non−repetitive motions and smooth transitions between them.
The second subsystem is a Behavior Engine that enables
authors to create sophisticated rules governing how actors
communicate, change, and make decisions. The combined
system provides an integrated set of tools for authoring the
"minds" and "bodies" of interactive actors. The system uses an
english−style scripting language so that creative experts who
are not primarily programmers can create powerful interactive
[Leuski10] Anton Leuski and David Traum. 2010. NPCEditor: A Tool for Building Question-Answering Characters. Proceedings of the Seventh conference on International Language Resources and Evaluation.
NPCEditor is a system for building and deploying virtual characters capable of engaging a user in spoken dialog on a limited domain. The dialogue may take any form as long as the character responses can be specified a priori. For example, NPCEditor has been used for constructing question answering characters where a user asks questions and the character responds, but other scenarios are possible. At the core of the system is a state of the art statistical language classification technology for mapping from user's text input to system responses. NPCEditor combines the classifier with a database that stores the character information and relevant language data, a server that allows the character designer to deploy the completed characters, and a user-friendly editor that helps the designer to accomplish both character design and deployment tasks. In the paper we define the overall system architecture, describe individual NPCEditor components, and guide the reader through the steps of building a virtual character.
[Blumberg95] Blumberg, Galyean. 1995. Multi-Level Direction of Autonomous Creatures for Real-Time Virtual Environments.
There have been several recent efforts to build behavior-based
autonomous creatures. While competent autonomous action is
highly desirable, there is an important need to integrate autonomy
with “directability”. In this paper we discuss the problem of building
autonomous animated creatures for interactive virtual environments
which are also capable of being directed at multiple levels.
We present an approach to control which allows an external entity
to “direct” an autonomous creature at the motivational level, the
task level, and the direct motor level. We also detail a layered
architecture and a general behavioral model for perception and
action-selection which incorporates explicit support for multi-level
direction. These ideas have been implemented and used to develop
several autonomous animated creatures.
[Doyle97] Doyle, Hayes-Roth. 1997. Agents in Annotated Worlds.
Virtual worlds offer great potential as environments for education, entertainment,
and collaborative work. Agents that function effectively in heterogeneous virtual
spaces must have the ability to acquire new behaviors and useful semantic
information from those contexts. The human-computer interaction literature
discusses how to construct spaces and objects that provide "knowledge in the
world" that aids human beings to perform these tasks. In this paper, we describe
how to build comparable annotated environments containing explanations of the
purpose and uses of spaces and activities that allow agents quickly to become
intelligent actors in those spaces. Examples are provided from our application
domain, believable agents acting as inhabitants and guides in a children’s
[Bickmore-aamas09] Timothy Bickmore, Daniel Schulman. 2009. A Virtual Laboratory for Studying Long-term Relationships between Humans and Virtual Agents. Proc. of 8th Int. Conf. on Autonomous Agents and Multiagent Systems.
Longitudinal studies of human-virtual agent interaction are
expensive and time consuming to conduct. We present a new
concept and tool for conducting such studies—the virtual
laboratory—in which a standing group of study participants
interacts periodically with a computer agent that can be remotely
manipulated to effect different study conditions, with outcome
measures also collected remotely. This architecture allows new
experiments to be dynamically defined and immediately
implemented in the continuously-running system without delays
due to recruitment and system reconfiguration. The use of this
tool in the study of a virtual agent that plays the role of an
exercise counselor for older adults is described, along with the
results of an initial experiment into the effects of conversational
variability on user engagement and exercise behavior.
[Bickmore-iva09] Timothy Bickmore, Daniel Schulman, and Langxuan Yin. 2009. Engagement vs. Deceit: Virtual Humans with Human Autobiographies. Proc. International Conf. on Intelligent Virtual Agents.
We discuss the ethical and practical issues involved in developing
virtual humans that relate personal, fictitious, human autobiographical stories
(“back stories”) to their users. We describe a virtual human exercise counselor
that interacts with users daily to promote exercise, and the integration of a
dynamic social storytelling engine used to maintain user engagement with the
agent and retention in the intervention. A longitudinal randomized controlled
experiment tested user attitudes towards the agent when it presented the stories
in first person (as its own history) compared to third person (as happening to
humans that it knew). Participants in the first person condition reported
enjoying their interactions with the agent significantly more and completed
more conversations with the agent, compared to participants in the third person
condition, while ratings of agent dishonesty were not significantly different
between the groups.
[Bates91] Joe Bates, Bryan Loyall, W. Scott Reilly. 1991. Broad Agents. Proceedings of the AAAI Spring Symposium on Integrated Intelligent Architectures.
[Marsella10] Stacy Marsella, Jonathan Gratch and Paolo Petta. Computational Models of Emotion. In in Scherer, K.R., Bänziger, T., & Roesch, E. (Eds.) A blueprint for a affective computing: A sourcebook and manual. Oxford: Oxford University Press, 2010
Recent years have seen a significant expansion in research on computational models of human emotional processes, driven both by their potential for basic research on emotion and cognition as well as their promise for an ever increasing range of applications. This has led to a truly interdisciplinary, mutually beneficial partnership between emotion research in psychology and computational science, of which this volume is an exemplar. To understand this partnership and its potential for transforming existing practices in emotion research across disciplines and for disclosing important novel areas of research, we explore in this chapter the history of work in computational models of emotion including the various uses to which they have been put, the theoretical traditions that have shaped their development, and how these uses and traditions are reflected in their underlying architectures.
[Bruner91] Bruner. 1991. The Narrative Construction of Reality. Critical Inquiry, 18(1), 1-21.
[Gerrig93] Gerrig. Experiencing Narrative Worlds. Chapters 1 and 3.
[Green00] Green, Brock. The Role of Transportation in the Persausiveness of Public Narratives. Journal of Personality ad Social Psychology, 79(5), 701-721.
Transportation was proposed as a mechanism whereby narratives can affect beliefs. Defined as absorption
into a story, transportation entails imagery, affect, and attentional focus. A transportation scale was
developed and validated. Experiment 1 (N = 97) demonstrated that extent of transportation augmented
story-consistent beliefs and favorable evaluations of protagonists. Experiment 2 (N = 69) showed that
highly transported readers found fewer false notes in a story than less-transported readers. Experiments 3
(N = 274) and 4 (A/ = 258) again replicated the effects of transportation on beliefs and evaluations; in
the latter study, transportation was directly manipulated by using processing instructions. Reduced
transportation led to reduced story-consistent beliefs and evaluations. The studies also showed that
transportation and corresponding beliefs were generally unaffected by labeling a story as fact or as
[Trabasso84] Trabasso, Secco, Van den Broek. 1984. Causal Cohesion and Story Coherence.
[Graesser94] Graesser, Singer, Trabasso. 1994. Constructing Inferences During Narrative Text Comprehension. Psychological Review, 101(3), 371-395.
The authors describe a constructionist theory that accounts for the knowledge-based inferences that
are constructed when readers comprehend narrative text. Readers potentially generate a rich variety
of inferences when they construct a referential situation model of what the text is about. The proposed
constructionist theory specifies that some, but not all, of this information is constructed under
most conditions of comprehension. The distinctive assumptions of the constructionist theory embrace
a principle of search (or effort) after meaning. According to this principle, readers attempt to
construct a meaning representation that addresses the reader's goals, that is coherent at both local
and global levels, and that explains why actions, events, and states are mentioned in the text. This
study reviews empirical evidence that addresses this theory and contrasts it with alternative theoretical
[Zwaan98] Rolf A. Zwaan and Gabriel A. Radvansky. Situation Models in Language Comprehension and Memory. Psychological Bulletin, 123(2): 162-185, 1998.
This article reviews research on the use of situation models in language comprehension and memory
retrieval over the past 15 years. Situation models are integrated mental representations of a described
state of affairs. Significant progress has been made in the scientific understanding of how situation
models are involved in language comprehension and memory retrieval. Much of this research focuses
on establishing the existence of situation models, often by using tasks that assess one dimension of
a situation model. However, the authors argue that the time has now come for researchers to begin
to take the multidimensionality of situation models seriously. The authors offer a theoretical framework
and some methodological observations that may help researchers to tackle this issue.
[Graesser91] Graesser, Lang, Roberts. 1991. Question Answering in the Context of Stories. Journal of Experimental Psychology: General, 120(3), 254-277.
In this study a model of question answering (called QUEST) is tested in the context of short
stories. College students first read a story and then judged the quality of answers to questions
about episodes in the story. The model could account for the goodness-of-answer judgments and
decision latencies for 5 categories of questions: why, how, when, enablement, and consequence.
QUEST specifies the information sources that are activated during question answering; the
content of each information source is structured according to a theory of knowledge representation.
QUEST specifies the convergence processes that dramatically narrow down the set of
possible answers (activated from the information sources) to a small set of good answers to a
[Bernardo94] Gerrig, Bernardo. 1994. Readers as Problem-Solvers in the Experience of Suspense. Poetics, 22, 459-472.
[Bal04] Bal. 2004. Narratology: Introduction to the Theory of Narrative. Chapter 1.
[Branigan] Branigan. Narrative Comprehension and Film. Chapter 3.
[Ryan] Ryan. Possible Worlds, Artificial Intelligence. Chapters 1-3.
[Schank81] Schank and Riesbeck. 1981. The Theory Behind the Programs: Conceptual Dependency. In Schank and Riesbeck (Eds.) Inside Computer Understanding: Five Programs Plus Miniatures.
[Cullingford81] Cullingford. 1981. SAM. In Schank and Riesbeck (Eds.) Inside Computer Understanding: Five Programs Plus Miniatures.
[Wilensky81] Wilensky. 1981. PAM. In Schank and Riesbeck (Eds.) Inside Computer Understanding: Five Programs Plus Miniatures.
[Lehnert82] Lehnert. 1982. Plot Units: A Narrative Summarization Strategy. In Lehnert and Ringle (Eds.) Strategies for Natural Language Processing
[Riloff10] Goyal, A., Riloff, E., Daume III, H. (2010) "Automatically Producing Plot Unit Representations for Narrative Text", Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP 2010).
In the 1980s, plot units were proposed as a
conceptual knowledge structure for representing and summarizing narrative stories. Our
research explores whether current NLP technology can be used to automatically produce
plot unit representations for narrative text. We
create a system called AESOP that exploits
a variety of existing resources to identify affect states and applies “projection rules” to
map the affect states onto the characters in a
story. We also use corpus-based techniques
to generate a new type of affect knowledge
base: verbs that impart positive or negative
states onto their patients (e.g., being eaten is
an undesirable state, but being fed is a desirable state). We harvest these “patient polarity verbs” from a Web corpus using two techniques: co-occurrence with Evil/Kind Agent
patterns, and bootstrapping over conjunctions
of verbs. We evaluate the plot unit representations produced by our system on a small collection of Aesop’s fables.
[Chambers08] Nathanael Chambers and Dan Jurafsky. 2008. Unsupervised Learning of Narrative Event Chains. In Proceedings of ACL/HLT 2008.
Hand-coded scripts were used in the 1970-80s
as knowledge backbones that enabled inference and other NLP tasks requiring deep semantic knowledge. We propose unsupervised
induction of similar schemata called narrative
event chains from raw newswire text.
A narrative event chain is a partially ordered
set of events related by a common protagonist. We describe a three step process to learning narrative event chains. The ﬁrst uses unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments. Thesecond applies a temporal classiﬁer to partially order the connected
events. Finally, the third prunes and clusters
self-contained chains from the space of events.
We introduce two evaluations: the narrative
cloze to evaluate event relatedness, and an order coherence task to evaluate narrative order.
We show a 36% improvement over baseline
for narrative prediction and 25% for temporal
[Mueller07] Erik T. Mueller. Modelling Space and Time in Narratives about Restaurants. Literary and Linguistic Computing Vol. 22, No. 1, 2007.
This study investigated the automatic modelling of space and time in narratives
involving dining in a restaurant. We built a program that (1) uses information
extraction techniques to convert narrative texts into templates containing key
information about the dining episodes discussed in the narratives, (2) constructs
commonsense reasoning problems from the templates, (3) uses commonsense
reasoning and a commonsense knowledge base to build models of the dining
episodes, and (4) generates and answers questions by consulting the models.
We describe the program and present the results of running it on a corpus of web
texts and American literature.
[Bares99] Bares, Lester. 1999. Intelligent Multi-shot Visualization Intefaces for Dynamic 3D Worlds. Proceedings of the 1999 International Conference on Intelligent User Interfaces.
In next-generation virtual 3D simulation, training, and
entertainment environments, intelligent visualization
interfaces must respond to user-specified viewing requests
so users can follow salient points of the action and monitor
the relative locations of objects. Users should be able to
indicate which object(s) to view, how each should be
viewed, cinematic style and pace, and how to respond when
a single satisfactory view is not possible. When constraints
fail, weak constraints can be relaxed or multi-shot solutions
can be displayed in sequence or as composite shots with
simultaneous viewports. To address these issues, we have
developed CONSTRAINTCAM, a real-time camera
visualization interface for dynamic 3D worlds. It has been
studied in an interactive testbed in which users can issue
viewing goals to monitor multiple autonomous characters
navigating through a virtual cityscape. CONSTRAINTCAM’s
real-time performance in this testbed is encouraging.
[He96] He, Cohen, Salesin. 1996. The Virtual Cinematographer: A Paradigm for Automatic Real-Time Camera Control and Directing. Proceedings of SIGGRAPH '96.
This paper presents a paradigm for automatically generating complete
camera specifications for capturing events in virtual 3D environments
in real-time. We describe a fully implemented system,
called the Virtual Cinematographer, and demonstrate its application
in a virtual “party” setting. Cinematographic expertise, in the form
of film idioms, is encoded as a set of small hierarchically organized
finite state machines. Each idiom is responsible for capturing a particular
type of scene, such as three virtual actors conversing or one
actor moving across the environment. The idiom selects shot types
and the timing of transitions between shots to best communicate
events as they unfold. A set of camera modules, shared by the idioms,
is responsible for the low-level geometric placement of specific
cameras for each shot. The camera modules are also responsible
for making subtle changes in the virtual actors’ positions to
best frame each shot. In this paper, we discuss some basic heuristics
of filmmaking and show how these ideas are encoded in the Virtual
[Thomlinson00] Thomlinson, Blumberg, and Nain. 2000. Expressive Autonomous Cinematography for Interactive Virtual Environments. Proceedings of the Fourth International Conference on Autonomous Agents.
We have created an automatic cinematography system for
interactive virtual environments. This system controls a virtual
camera and lights in a three-dimensional virtual world inhabited
by a group of autonomous and user-controlled characters. By
dynamically changing the camera and the lights, our system
facilitates the interaction of human participants with this world
and displays the emotional content of the digital scene.
Building on the tradition of cinema, modern video games, and
autonomous behavior systems, we have constructed this
cinematography system with an ethologically-inspired structure
of sensors, emotions, motivations, and action-selection
mechanisms. Our system breaks shots into elements, such as
which actors the camera should focus on or the angle it should
use to watch them. Hierarchically arranged cross-exclusion
groups mediate between the various options, arriving at the best
shot at each moment in time. Our cinematography system uses
the same approach that we use for our virtual actors. This eases
the cross-over of information between them, and ultimately leads
to a richer and more unified installation.
As digital visualizations grow more complex, cinematography
must keep pace with the new breeds of characters and scenarios.
A behavior-based autonomous cinematography system is an
effective tool in the creation of interesting virtual worlds. Our
work takes first steps toward a future of interactive, emotional
[Jhala10] Jhala, Young. 2006. Cinematic Visual Discourse: Representation, Generation, and Evaluation. IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES, VOL. 2, NO. 2, JUNE 2010
In this paper, we present the design, implementation,
and evaluation of an end-to-end camera planning system called
Darshak. Darshak automatically constructs cinematic narrative
discourse of a given story in a 3-D virtual environment. It utilizes a
hierarchical partial-order causal link (POCL) planning algorithm
to generate narrative plans that contain story events and camera
directives for filming them. Dramatic situation patterns, commonly
used by writers of fictional narratives, are formalized as
communicative plan operators that provide a basis for structuring
the cinematic content of the story’s visualization. The dramatic
patterns are realized through abstract communicative operators
that represent operations on a viewer’s beliefs about the story and
its telling. Camera shot compositions and transitions are defined
in this plan-based framework as execution primitives. Darshak’s
performance is evaluated through a novel user study based on
techniques used to evaluate existing cognitive models of narrative
comprehension. Initial study reveals significant effect of the choice
of visualization strategies on measured viewer comprehension. It
further shows significant effect of Darshak’s choice of visualization
strategy on comprehension.
[Elson07] Elson, Riedl. 2007. A Lightweight Intelligent Virtual Cinematography System for Machinima Production. Proceedings of the 3rd Conference on Artificial Intelligence and Interactive Digital Entertainment
Machinima is a low-cost alternative to full production
filmmaking. However, creating quality cinematic
visualizations with existing machinima techniques still
requires a high degree of talent and effort. We introduce a
lightweight artificial intelligence system, Cambot, that can
be used to assist in machinima production. Cambot takes a
script as input and produces a cinematic visualization.
Unlike other virtual cinematography systems, Cambot
favors an offline algorithm coupled with an extensible
library of specific modular and reusable facets of cinematic
knowledge. One of the advantages of this approach to
virtual cinematography is a tight coordination between the
positions and movements of the camera and the actors.
[Boden09] Boden. 2009. Computer Models of Creativity. AI Magazine.
[Wiggins06] Wiggins. 2006. Searching for Computational Creativity. New Generation Computing, 24.
Boden's philosophical account of creativity has been criticised
on the grounds that it does not properly capture some aspects of creative
situations. Wiggins has presented a formalisation of Boden's account,
which allows such issues to be examined more precisely. We explore the relationship
between traditional AI search methods and Boden's abstraction
of creative behaviour, and revisit Bundy's argument in the context of that
[Ritchie01] Ritchie. 2001. Assessing Creativity. Proceedings of AISB Symposium on AI and Creativity in Arts and Science.
In exploring the question of whether a computer program is behaving creatively, it is important to be explicit, and if
possible formal, about the criteria that are being applied in making judgements of creativity. We propose a formal (and
rather simplified) outline of the relevant attributes of a potentially creative program. Based on this, we posit a number of
formal criteria that could be applied to rate the extent to which the program has behaved creatively. A guiding principle
is that the question of what computational mechanisms might lead to creative behaviour is open and empirical, and
hence we should clearly distinguish between judgements about creative achievements and theoretical proposals about
potentially creative mechanisms. The intention is to focus, clarify and make more concrete the debate about creative