Unsupervised Modeling of Player Style With LDA

Gow, Jeremy; Baumgarten, Robin; Cairns, Paul; Colton, Simon; Miller, Paul

doi:10.1109/tciaig.2012.2213600

Cited by 40 publications

(23 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Now that it has been shown that player input is a viable predictor of player skill, further analysis is required in order to uncover more patterns in play. As in other research [14], unsupervised techniques could be used to cluster players by their input. This could help prediction accuracy and aid in more rigorous extraction of features.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting skill from gameplay input to a first-person shooter

Buckley

Chen

Knowles

2013

2013 IEEE Conference on Computational Inteligence in Games (CIG)

View full text Add to dashboard Cite

Abstract-One way to make video games more attractive to a wider audience is to make them adaptive to players. The preferences and skills of players can be determined in a variety of ways, but should be done as unobtrusively as possible to keep the player immersed. This paper explores how gameplay input recorded in a first-person shooter can predict a player's ability. As these features were able to model a player's skill with 76% accuracy, without the use of game-specific features, we believe their use would be transferable across similar games within the genre.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Previous work has successfully clustered players by their playing style [14]. For a 2-D arcade game Snakeotron, the features corresponding to player input were considered very important.…”

Section: Introductionmentioning

confidence: 99%

Predicting skill from gameplay input to a first-person shooter

Buckley

Chen

Knowles

2013

2013 IEEE Conference on Computational Inteligence in Games (CIG)

View full text Add to dashboard Cite

show abstract

“…Previous work has found different player types in many games using various methods of clustering [25], [26], [27]. Decision trees, as demonstrated in this paper, are a suitable representation of play style and could help with the understanding of the differences between these player types due to the ease of comparing their human readable model.…”

Section: B Understanding Human Play Stylementioning

confidence: 94%

Player Preference and Style in a Leading Mobile Card Game

Cowling

Devlin

Powley³

et al. 2015

IEEE Trans. Comput. Intell. AI Games

View full text Add to dashboard Cite

Abstract-Tuning game difficulty prior to release requires careful consideration. Players can quickly lose interest in a game if it is too hard or too easy. Assessing how players will cope prior to release is often inaccurate. However, modern games can now collect sufficient data to perform large scale analysis postdeployment and update the product based on these insights.AI Factory Spades is currently the top rated Spades game in the Google Play store. In collaboration with the developers, we have collected gameplay data from 27 592 games and statistics regarding wins/losses for 99 866 games using Google Analytics. Using the data collected, this study analyses the difficulty and behaviour of an Information Set Monte Carlo Tree Search player we developed and deployed in the game previously [1].The methods of data collection and analysis presented in this study are generally applicable. The same workflow could be used to analyse the difficulty and typical player or opponent behaviour in any game. Furthermore, addressing issues of difficulty or non-human-like opponents post-deployment can positively affect player retention.

show abstract

“…Ramirez-Cano et al [71] cluster players of an action-hunting game using a three-level ''meta-clustering'' form of analysis. Gower et al [72] describe players of two different action games using multi-class Linear Discriminant Analysis (LDA).…”

Section: In-game Player Behaviourmentioning

confidence: 99%

“…The exception is [72], which reduces the dimensionality of in-game behaviour data to produce a trait-like description of players, rather than assigning each player to a set of distinct player types. For reasons discussed in Section 2, we view a type-based description of players to be an oversimplification that, if evaluated, is likely to have only a limited effect on the player's experience when applied to personalisation.…”

Section: In-game Player Behaviourmentioning

confidence: 99%