Crowdsourcing the Aesthetics of Platform Games

  title={Crowdsourcing the Aesthetics of Platform Games},
  author={Noor Shaker and Georgios N. Yannakakis and Julian Togelius},
  journal={IEEE Transactions on Computational Intelligence and AI in Games},
What are the aesthetics of platform games and what makes a platform level engaging, challenging, and/or frustrating? We attempt to answer such questions through mining a large set of crowdsourced gameplay data of a clone of the classic platform game Super Mario Bros (SMB). The data consist of 40 short game levels that differ along six key level design parameters. Collectively, these levels are played 1560 times over the Internet, and the perceived experience is annotated by experiment… 

Platformer level design for player believability

This paper crowdsource rank-based annotations from subjects that view playthrough videos of various AI and human controlled agents in platformer levels of dissimilar characteristics and builds support vector machine models of reported believability based on gameplay and level features which are extracted from the videos.

StreamLevels : Automatic Balancement of Platform Levels

A visual tool that helps the designer in balancing difficulty inside the process of level design and allows the designer to create new levels by drawing streamlines interactively.

Towards Challenge Balancing for Personalised Game Spaces

The approach specically considers two persisting design challenges, namely implicit user feedback and high risk of user abandonment and a clear separation between (intelligent) offine exploration and (safety-conscious) online exploitation.

Challenge balancing for personalised game spaces

This paper contributes an approach that acknowledges that for effective online game personalisation, one needs to rapidly converge to an appropriate policy for the individual user in online gameplay - employing the learned feedback model and a straightforward model of user abandonment.

Modelling Affect for Horror Soundscapes

This paper explores the creation of computational models capable of ranking short audio pieces based on crowdsourced annotations of tension, arousal and valence based on support vector machines, whose inputs are low-level features extracted from the audio assets of a comprehensive sound library.

UvA-DARE ( Digital Academic Repository ) Challenge Balancing for Personalised Game Spaces

In this paper we propose an approach for personalising the space in which a game is played (i.e., levels) – to the end of tailoring the experienced challenge to the individual user during actual play

The platformer experience dataset

The Platformer Experience Dataset (PED) is introduced - the first open-access game experience corpus - that contains multiple modalities of user data of Super Mario Bros players that aims to be used for player experience capture through context-based (i.e. game content), behavioral and visual recordings of platform game players.

Generating Entertaining Platform Game Levels

This dissertation consisted in the usage of machine learning techniques to generate platform levels for the known platform game Super Mario Bros., having the fun factor severely emphasized.

Procedural Generation of Game Maps With Human-in-the-Loop Algorithms

The results show that the human computation approach to evaluate small portions of levels generated by an off-the-shelf generation system for the game of Infinite Mario Bros. to generate levels that are perceived by people to have better visual aesthetics and to be more enjoyable to play than existing approaches.

The Platformer Experience Dataset CONFERENCE

The Platformer Experience Dataset (PED) is introduced — the first open-access game experience corpus — that contains multiple modalities of user data of Super Mario Bros players that aims to be used for player experience capture through contextbased (i.e. game content), behavioral and visual recordings of platform game players.



Feature analysis for modeling game content quality

A method to extract the most useful information about game content from short game sessions is introduced by investigating the size of game session that yields the highest accuracy in predicting players' preferences, and by defining the smallest game session size for which the model can still predict reported emotion with acceptable accuracy.

A Theory of Fun for Game Design

Now in full color, the 10th anniversary edition of this classic book takes you deep into the influences that underlie modern video games, and examines the elements they share with traditional games

A framework for analysis of 2D platformer levels

The framework provides a common vocabulary for these items and provides level designers with a method for thinking about elements of platformers and how to compose them to create interesting and challenging levels.

Modeling player experience in Super Mario Bros

Results show that challenge and frustration can be predicted with a high accuracy via a simple single-neuron model whereas model accuracy for fun suggests the use of more complex non-linear approximators for this emotion.

Modeling Player Experience for Content Creation

In this paper, we use computational intelligence techniques to built quantitative models of player experience for a platform game. The models accurately predict certain key affective states of the

Towards Automatic Personalized Content Generation for Platform Games

It is shown that personalized levels can be automatically generated for platform games using more accurate models based on a much larger data set and a mechanism for adapting level design parameters to given players and playing style.

Visualizing and understanding players' behavior in video games: discovering patterns and supporting aggregation and comparison

A new visualization system that allows analysts to build visualization and interact with telemetry data, to identify patterns and identify game design issues efficiently is presented and a new approach to visualize players' behavior that has not been explored so far is proposed.

Guess What? A Game for Affective Annotation of Video Using Crowd Sourcing

One of the most time consuming and laborious problems facing researchers in Affective Computing is annotation of data, particularly with the recent adoption of multimodal data. Other fields, such as

A Generic Approach to Challenge Modeling for the Procedural Creation of Video Game Levels

This top-down approach improves upon typical bottom-up techniques in providing semantically meaningful parameters such as difficulty and player skill, in giving human designers considerable control over the output of the generative system, and in offering the ability to create levels for different types of games.

What makes computer games fun? (abstract only)

Review of the home computer market shows what can be accomplished by an easy-to-use accounting aid through advertising store demonstrations, and word of mouth.