Predicting Tetris Performance Using Early Keystrokes
Guglielmo,Gianluca Klincewicz,Michal Veld,Elisabeth Huis in 't Spronck,Pieter
Guglielmo,Gianluca
Klincewicz,Michal
Veld,Elisabeth Huis in 't
Spronck,Pieter
Abstract
In this study, we predict the different levels of performance in a Nintendo Entertainment System (NES) Tetris session based on the score and the number of matches played by the players. Using the first 45 seconds of gameplay, a Random Forest Classifier was trained on the five keys used in the game obtaining a ROC-AUC score of 0.80. Further analysis revealed that the number of down keys (forced drop) and the number of left keys (left translation) are the most relevant keys in this task, showing that by merely including the data from these two keys our Random Forest Classifier reached a ROC-AUC score of 0.83. We conclude that the keylogger data during the early phases of a game session can be successfully used to predict performance in longer sessions of Tetris.
Description
Funding Information: The research reported in this study is funded by the MasterMinds and Data2Game projects, part of the RegionDeal Midland WestBra-bant, and is co-funded by the Ministry of Economic Affairs, Region Hart van Brabant, REWIN, Region West-Brabant, Midpoint Brabant, Municipality of Breda, Netherlands Research Organisation (NWO), and Municipality of Tilburg awarded to MML Publisher Copyright: © 2023 Owner/Author.
Date
2023-04-12
Journal Title
Journal ISSN
Volume Title
Publisher
ACM
Research Projects
Organizational Units
Journal Issue
Keywords
Expertise, Machine Learning, Performance, Peripherals, Tetris, Video games
Citation
Guglielmo, G, Klincewicz, M, Veld, E H I & Spronck, P 2023, Predicting Tetris Performance Using Early Keystrokes. in P Lopes, F Luz, A Liapis & H Engstrom (eds), Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023., 46, ACM International Conference Proceeding Series, ACM, pp. 1-4, FDG 2023: Foundations of Digital Games 2023 Lisbon Portugal, Lisbon, Portugal, 12/04/23. https://doi.org/10.1145/3582437.3587184
License
info:eu-repo/semantics/openAccess