Player modeling and estimation of player experience have become very active research fields within affective computing, human computer interaction, and game artificial intelligence in recent years. For advancing our knowledge and understanding on player experience, we introduce the Platformer Experience Dataset (PED) — the first open-access game experience corpus — that contains multiple modalities of user data of Super Mario Bros players. The open-access database aims to be used for player experience capture through context based (i.e. game content), behavioral and visual recordings of platform game players. In addition, the database contains demographical data of the players and self-reported annotations of experience in two forms: ratings and ranks. PED opens up the way to desktop and console games that use video from web cameras and visual sensors and offer possibilities for holistic player experience modeling approaches that can, in turn, yield richer game personalization.

Dataset Description:

There are fifty eight volunteers participated in the recording sessions (28 male, with player age ranging from 22 to 48 years), which took place in Denmark (with participants of different ethnic backgrounds) and Greece (with mostly Greek participants).  Participants played a total of 321 games (more than 6 hours of recording in total).

The dataset contains demographic information about participants' gender, age, frequency of playing games, hours spent on gameplay on a weekly basis and any previous experience with Super Mario Bros.

Players played level A and had three chances to finish it after which they were presented with a rating questionnaire which asked them to report their level of engagement, frustration and challenge in a scale between 0 to 4 (0 denoting “not at all’’, 4 meaning “extremely’’). The process was then repeated with a different game level (level B) and another rating questionnaire.

After completing these two games, players were asked to report which of the two games they preferred via a 4-alternative forced choice (4- AFC) questionnaire protocol: A over B; B over A; both equally engaging/frustrating/challenging; both equally not preferred.

Finally, players were given the option to play more pairs of games (most of them did) or quit the game.

Player Behaviour Data:

The logged features available with the dataset are: level completion; Mario death and the cause of death; bumping into blocks and picking up bonuses as an absolute number and percentage of total; killing enemies; changing mode and time spent in small, big or fire mode; changing direction and time spent moving left, right, jumping, ducking and running; and the full trajectory of Mario as a combination of temporal events.

Visual Features:

The dataset contains the complete  video stream associated with each gameplay session.

More Details:

A complete description of the database can be found in: K. Karpouzis, N. Shaker, G. Yannakakis, S. Asteriadis. The Platformer Experience Dataset, 6th Affective Computing and Intelligent Interaction (ACII 2015) Conference, Xi’an, China, 21-24 September, 2015

For further details about the development and analysis of the dataset. Please refer to:

1. K. Karpouzis, N. Shaker, G. Yannakakis, S. Asteriadis. The Platformer Experience Dataset, 6th Affective Computing and Intelligenct Interaction (ACII 2015) Conference, Xi’an, China, 21-24 September, 2015.
2. Noor Shaker, Stylianos Asteriadis, Georgios Yannakakis and Kostas Karpouzis. Fusing Visual and Behavioral Cues for Modeling User Experience in Games, IEEE Transactions on System Man and Cybernetics, Special Issue on Modern Control for Computer Games, 2012.
3. Stylianos Asteriadis, Kostas Karpouzis, Noor Shaker and Georgios Yannakakis. Towards Detecting Clusters of Players using Visual and Game-play Behavioral Cues,  in Proceedings of the 4th International Conference on Games and Virtual Worlds for Serious Applications (VS-GAMES12), Genoa, Italy, 2012.
4. Stylianos Asteriadis, Kostas Karpouzis, Noor Shaker and Georgios Yannakakis. Does your profile say it all? Using demographics to predict expressive head movement during gameplay,  in 20th conference on User Modeling, Adaptation, and Personalization (UMAP 2012), Workshop on TV and multimedia personalization, Montreal, Canada, 2012. 
5. Stylianos Asteriadis, Noor Shaker, Kostas Karpouzis and Georgios Yannakakis. Towards Player’s Affective and Behavioral Visual Cues as drives to Game Adaptation,  LREC Workshop on Multimodal Corpora for Machine Learning, Istanbul, May, 2012. 
6. Noor Shaker, Stylianos Asteriadis, Georgios Yannakakis and Kostas Karpouzis. A Game-based Corpus for Analysing the Interplay between Game Context and Player Experience, in Proceedings of  the 2011 Affective Computing and Intelligent Interaction Conference (ACII 2011), 2011. 

Contact

If you have any question, please send me an email.