This paper describes computational processes which can simulate how human designers sketch and then iteratively refine their work. The paper uses the concept of a map sketch as an initial, low-resolution and low-fidelity prototype of a game level, and suggests how such map sketches can be refined computationally. Different case studies with map sketches of different genres showcase how refinement can be achieved via increasing the resolution of the game level, increasing the fidelity of the function which evaluates it, or a combination of the two. While these case studies use genetic algorithms to automatically generate levels at different degrees of refinement, the general method described in this paper can be used with most procedural generation methods, as well as for AI-assisted design alongside a human creator.

This paper introduces a search-based generative process for first person shooter levels. Genetic algorithms evolve the level's architecture and the placement of powerups and player spawnpoints, generating levels with one floor or two floors. The evaluation of generated levels combines metrics collected from simulations of artificial agents competing in the level and theory-based heuristics targeting general level design patterns. Both simulation-based and theory-driven evaluations target player balance and exploration, while resulting levels emergently exhibit several popular design patters of shooter levels.

Artificial Intelligence (AI) techniques have been widely used in video games to control non-playable characters. More recently, AI has been applied to automated story generation with the objective of managing the player's experience in an interactive narrative. Such AI experience managers can generate and adapt narrative dynamically, often in response to the player's in-game actions. We implement and evaluate a recently proposed AI experience manager, PACE, which predicts the player's emotional response to a narrative event and uses such predictions to shape the narrative to keep the player on an author-supplied target emotional curve.

Dunyazad is a system which creates narrative choices à la Choose-Your-Own-Adventure books. It attempts to generate choices that achieve specific poetic effects. This paper demonstrates Dunyazad’s ability to manage player expectations by having it generate three distinct choice structures: obvious choices, relaxed choices, and dilemmas. Using answer set programming, Dunyazad’s choice generation system directly encodes a theory of choice poetics, so flaws in its output can inform both the system and the theory itself. Survey data presented here thus not only validate that players’ perceptions match Dunyazad’s intentions, but also have implications for the theory of choice poetics. Statistical analysis of our data indicates that Dunyazad can successfully construct obvious choices, relaxed choices, and dilemmas.

There are several approaches in the literature for automatically generating Infinite Mario Bros levels. The evaluation of such approaches is often performed solely with computational metrics such as leniency and linearity. While these metrics are important for an initial exploratory evaluation of the content generated, it is not clear whether they are able to capture the player's perception of the content generated. In this paper we evaluate several of the commonly used computational metrics. Namely, we perform a systematic user study with procedural content generation systems and compare the insights gained from our user study with those gained from analyzing the computational metric values. The results of our experiment suggest that current computational metrics should not be used in lieu of user studies for evaluating content generated by computer programs.

Horror games form a peculiar niche within game design paradigms, as they entertain by eliciting negative emotions such as fear and unease to their audience during play. This genre often follows a specific progression of tension culminating at a metaphorical peak, which is defined by the designer. A player's tension is elicited by several facets of the game, including its mechanics, its sounds, and the placement of enemies in its levels. This paper investigates how designers can control and guide the automated generation of levels and their soundscapes by authoring the intended tension of a player traversing them.

Indexter is a plan-based computational model of narrative discourse which leverages cognitive scientific theories of how events are stored in memory during online comprehension. These discourse models are valuable for static and interactive narrative generation systems because they allow the author to reason about the audience's understanding and attention as they experience a story. A pair of Indexter events can share up to five indices: protagonist , time , space , causality , and intentionality . We present the first in a planned series of evaluations that will explore increasingly nuanced methods of using these indices to predict salience. The Pairwise Event Salience Hypothesis states that when a past event shares one or more indices with the most recently narrated event, that past event is more salient than one which shares no indices with the most recently narrated event. A crowd-sourced (n=200) study of 24 short text stories that control for content, text, and length supports this hypothesis. While this is encouraging, we believe it also motivates the development of a richer model that accounts for intervening events, narrative complexity, and episodic memory decay.

Online strategy video games offer several unique challenges to the field of AI research. Due to their large state and action spaces, existing search algorithms have difficulties in making strategically strong decisions. Additionally, the nature of competitive on-line video games adds the requirement that game designers be able to tweak game properties regularly when strategic imbalances are found. This means that an AI system for a game like this needs to be robust to such changes and less reliant on expert knowledge. This paper makes two main contributions to advancing the state of the art for AI in modern strategy video games which have large state and action spaces. The first is a novel method for performing hierarchical search using a portfolio of algorithms to reduce the search space while maintaining strong action candidates. The second contribution is an overall AI architecture for strategy video games using this portfolio search method. The proposed methods are used as the AI system for Prismata, an online turn-based strategy game by Lunarch Studios. This system is evaluated using three experiments: on-line play vs.~human players, off-line AI tournaments to test the relative strengths of the AI bots, and a survey to determine user satisfaction of the system so far. Our result show that this system achieves a skill level in the top 25% of human players on the ranked ladder, can be modified quickly to create different difficulty settings, is robust to changes in game unit properties, and creates an overall AI experience which is user rated more enjoyable than those currently found in similar video games.

Community Question Answering (CQA) websites are a popular tool for internet users to fulfill diverse information needs. Posted questions can be multiple sentences long and span diverse domains. They go beyond factoid questions and can be conversational, opinion-seeking and experiential questions, that might have multiple, potentially conflicting, useful answers from different users. In this paper, we describe a large-scale formative study to collect commonsense properties of questions and answers from 18 diverse communities from stackexchange.com. We collected 50,000 human judgments on 500 question-answer pairs. Commonsense properties are features that humans can extract and characterize reliably by using their commonsense knowledge and native language skills, and no special domain expertise is assumed. We report results and suggestions for designing human computation tasks for collecting commonsense semantic judgments.

This paper examines the importance of presenting simple, intuitive tasks when conducting microtasking on crowdsourcing platforms. Most crowdsourcing platforms allow the maker of a task to present any length of instructions to crowd workers who participate in their tasks. Our experiments show, however, most workers who participate in crowdsourcing microtasks do not read the instructions, even when they are very brief. To facilitate success in microtask design, we highlight the importance of making simple, easy to grasp tasks that do not rely on instructions for explanation.