The Arousal video Game AnnotatIoN (AGAIN) Dataset

Melhart, David; Liapis, Antonios; Yannakakis, Georgios N.

doi:10.48550/arxiv.2104.02643

Cited by 7 publications

(17 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study employs the AGAIN dataset 1 , which was designed to provide a diverse and robust database for general affect modelling in the domain of videogames [7]. The raw dataset includes 1, 116 playthroughs; after cleaning and preprocessing, the clean dataset (used in this paper) includes 122 participants and 995 playthroughs.…”

Section: The Again Datasetmentioning

confidence: 99%

“…The raw dataset includes 1, 116 playthroughs; after cleaning and preprocessing, the clean dataset (used in this paper) includes 122 participants and 995 playthroughs. More information on the games, the cleaning process, and the dataset are found in [7].…”

Section: The Again Datasetmentioning

confidence: 99%

“…The clean AGAIN dataset consists of 122 players playing 995 sessions of 2-minute games [7]. The gender distribution of the participants skews towards men.…”

Section: B Datasetmentioning

confidence: 99%

“…only bots and objects visible to the player are logged. Specific features encode the gameplay context, player status, bot status, and events both controlled by the player and controlled by the game; more details can be found at [7]. Some games lack gameplay features that other games have, even within the same genre.…”

Section: B Datasetmentioning

confidence: 99%

“…Then we examine whether certain adhoc designed features that contain general information about gameplay can act as reliable general predictors of player experience across games of the same genre. We use the Affect Game AnnotatIoN (AGAIN) dataset [7], which includes telemetry and annotations of arousal for almost 1,000 play sessions of nine different games across three different genres (Racing, Shooter, and Platformer). We employ random forests for preference learning in order to build models that predict arousal both in a specific game and across unseen games of each genre (see Figure 1).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Towards General Models of Player Experience: A Study Within Genres

Melhárt¹,

Liapis²,

Yannakakis³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

To which degree can abstract gameplay metrics capture the player experience in a general fashion within a game genre? In this comprehensive study we address this question across three different videogame genres: racing, shooter, and platformer games. Using high-level gameplay features that feed preference learning models we are able to predict arousal accurately across different games of the same genre in a largescale dataset of over 1, 000 arousal-annotated play sessions. Our genre models predict changes in arousal with up to 74% accuracy on average across all genres and 86% in the best cases. We also examine the feature importance during the modelling process and find that time-related features largely contribute to the performance of both game and genre models. The prominence of these game-agnostic features show the importance of the temporal dynamics of the play experience in modelling, but also highlight some of the challenges for the future of general affect modelling in games and beyond.

show abstract

Section: The Again Datasetmentioning

confidence: 99%

Section: The Again Datasetmentioning

confidence: 99%

“…The clean AGAIN dataset consists of 122 players playing 995 sessions of 2-minute games [7]. The gender distribution of the participants skews towards men.…”

Section: B Datasetmentioning

confidence: 99%

Section: B Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Towards General Models of Player Experience: A Study Within Genres

Melhárt¹,

Liapis²,

Yannakakis³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Learning Task-Independent Game State Representations from Unlabeled Images

Trivedi

Makantasis

Liapis

et al. 2022

2022 IEEE Conference on Games (CoG)

View full text Add to dashboard Cite

On-screen game footage contains rich contextual information that players process when playing and experiencing a game. Learning pixel representations of games can benefit artificial intelligence across several downstream tasks including game-playing agents, procedural content generation, and player modelling. The generalizability of these methods, however, remains a challenge, as learned representations should ideally be shared across games with similar game mechanics. This could allow, for instance, game-playing agents trained on one game to perform well in similar games with no re-training. This paper explores how generalizable pre-trained computer vision encoders can be for such tasks, by decomposing the latent space into content embeddings and style embeddings. The goal is to minimize the domain gap between games of the same genre when it comes to game content critical for downstream tasks, and ignore differences in graphical style. We employ a pre-trained Vision Transformer encoder and a decomposition technique based on game genres to obtain separate content and style embeddings. Our findings show that the decomposed embeddings achieve style invariance across multiple games while still maintaining strong content extraction capabilities. We argue that the proposed decomposition of content and style offers better generalization capacities across game environments independently of the downstream task.

show abstract

From the Lab to the Wild: Affect Modeling Via Privileged Information

Makantasis

Pinitas²,

Liapis³

et al. 2024

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

How can we reliably transfer affect models trained in controlled laboratory conditions (in-vitro) to uncontrolled real-world settings (in-vivo)? The information gap between in-vitro and in-vivo applications defines a core challenge of affective computing. This gap is caused by limitations related to affect sensing including intrusiveness, hardware malfunctions and availability of sensors. As a response to these limitations, we introduce the concept of privileged information for operating affect models in real-world scenarios (in the wild). Privileged information enables affect models to be trained across multiple modalities available in a lab, and ignore, without significant performance drops, those modalities that are not available when they operate in the wild. Our approach is tested in two multimodal affect databases one of which is designed for testing models of affect in the wild. By training our affect models using all modalities and then using solely raw footage frames for testing the models, we reach the performance of models that fuse all available modalities for both training and testing. The results are robust across both classification and regression affect modeling tasks which are dominant paradigms in affective computing. Our findings make a decisive step towards realizing affect interaction in the wild.

show abstract

The Arousal video Game AnnotatIoN (AGAIN) Dataset

Cited by 7 publications

References 49 publications

Towards General Models of Player Experience: A Study Within Genres

Towards General Models of Player Experience: A Study Within Genres

Learning Task-Independent Game State Representations from Unlabeled Images

From the Lab to the Wild: Affect Modeling Via Privileged Information

Contact Info

Product

Resources

About