Analysing the Relevance of Experience Partitions to the Prediction of Players’ Self-Reports of Affect

Héctor Pérez Martínez; Georgios N. Yannakakis

Analysing the Relevance of Experience Partitions to the Prediction of Players’ Self-Reports of Affect

Héctor Pérez Martínez, Georgios N. Yannakakis

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

A common practice in modeling affect from physiological signals consists of reducing the signals to a set of statistical features that feed predictors of self-reported emotions. This paper analyses the impact of various time-windows, used for the extraction of physiological features, to the accuracy of affective models of players in a simple 3D game. Results show that the signals recorded in the central part of a short gaming experience contain more relevant information to the prediction of positive affective states than the starting and ending parts while the relevant information to predict anxiety and frustration appear not to be localized in a specific time interval but rather dependent on particular game stimuli.

Original language	English
Title of host publication	ACII'11 Proceedings of the 4th international conference on Affective computing and intelligent interaction : Workshop on Emotion in Games (EMO games)
Number of pages	9
Publisher	Springer
Publication date	2011
Pages	538-546
ISBN (Print)	978-3-642-24570-1
Publication status	Published - 2011

Keywords

Affective Computing
Physiological Signals
Feature Extraction
Time-Windows
Game-Based Emotion Prediction

Cite this

@inproceedings{6ecac6188c4a4d2892a97d4079b68e3e,

title = "Analysing the Relevance of Experience Partitions to the Prediction of Players{\textquoteright} Self-Reports of Affect",

abstract = "A common practice in modeling affect from physiological signals consists of reducing the signals to a set of statistical features that feed predictors of self-reported emotions. This paper analyses the impact of various time-windows, used for the extraction of physiological features, to the accuracy of affective models of players in a simple 3D game. Results show that the signals recorded in the central part of a short gaming experience contain more relevant information to the prediction of positive affective states than the starting and ending parts while the relevant information to predict anxiety and frustration appear not to be localized in a specific time interval but rather dependent on particular game stimuli.",

keywords = "Affective Computing, Physiological Signals, Feature Extraction, Time-Windows, Game-Based Emotion Prediction, Affective Computing, Physiological Signals, Feature Extraction, Time-Windows, Game-Based Emotion Prediction",

author = "Mart{\'i}nez, {H{\'e}ctor P{\'e}rez} and Yannakakis, {Georgios N.}",

year = "2011",

language = "English",

isbn = "978-3-642-24570-1 ",

pages = "538--546",

booktitle = "ACII'11 Proceedings of the 4th international conference on Affective computing and intelligent interaction",

publisher = "Springer",

address = "Germany",

}

Analysing the Relevance of Experience Partitions to the Prediction of Players’ Self-Reports of Affect. / Martínez, Héctor Pérez; Yannakakis, Georgios N.
ACII'11 Proceedings of the 4th international conference on Affective computing and intelligent interaction: Workshop on Emotion in Games (EMO games). Springer, 2011. p. 538-546.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Analysing the Relevance of Experience Partitions to the Prediction of Players’ Self-Reports of Affect

AU - Martínez, Héctor Pérez

AU - Yannakakis, Georgios N.

PY - 2011

Y1 - 2011

N2 - A common practice in modeling affect from physiological signals consists of reducing the signals to a set of statistical features that feed predictors of self-reported emotions. This paper analyses the impact of various time-windows, used for the extraction of physiological features, to the accuracy of affective models of players in a simple 3D game. Results show that the signals recorded in the central part of a short gaming experience contain more relevant information to the prediction of positive affective states than the starting and ending parts while the relevant information to predict anxiety and frustration appear not to be localized in a specific time interval but rather dependent on particular game stimuli.

AB - A common practice in modeling affect from physiological signals consists of reducing the signals to a set of statistical features that feed predictors of self-reported emotions. This paper analyses the impact of various time-windows, used for the extraction of physiological features, to the accuracy of affective models of players in a simple 3D game. Results show that the signals recorded in the central part of a short gaming experience contain more relevant information to the prediction of positive affective states than the starting and ending parts while the relevant information to predict anxiety and frustration appear not to be localized in a specific time interval but rather dependent on particular game stimuli.

KW - Affective Computing

KW - Physiological Signals

KW - Feature Extraction

KW - Time-Windows

KW - Game-Based Emotion Prediction

KW - Affective Computing

KW - Physiological Signals

KW - Feature Extraction

KW - Time-Windows

KW - Game-Based Emotion Prediction

M3 - Article in proceedings

SN - 978-3-642-24570-1

SP - 538

EP - 546

BT - ACII'11 Proceedings of the 4th international conference on Affective computing and intelligent interaction

PB - Springer

ER -

Analysing the Relevance of Experience Partitions to the Prediction of Players’ Self-Reports of Affect

Abstract

Keywords

Fingerprint

Cite this