Automatic Cognitive Load Classification Using High-Frequency Interaction Events: An Exploratory Study

Automatic Cognitive Load Classification Using High-Frequency Interaction Events: An Exploratory Study

Tao Lin (Department of Computer Science, Sichuan University, Chengdu, China), Xiao Li (Department of Computer Science, Sichuan University, Chengdu, China), Zhiming Wu (Department of Computer Science, Sichuan University, Chengdu, China) and Ningjiu Tang (Department of Computer Science, Sichuan University, Chengdu, China)
Copyright: © 2013 |Pages: 16
DOI: 10.4018/jthi.2013070106
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

There is still a challenge of creating an evaluation method which can not only unobtrusively collect data without supplement equipment but also objectively, quantitatively and in real-time evaluate cognitive load of user based the data. The study explores the possibility of using the features extracted from high-frequency interaction events to evaluate cognitive load to respond to the challenge. Specifically, back-propagation neural networks, along with two feature selection methods (nBset and SFS), were used as the classifier and it was able to use a set of features to differentiate three cognitive load levels with an accuracy of 74.27%. The main contributions of the research are: (1) demonstrating the use of combining machine learning techniques and the HFI features in automatically evaluating cognitive load; (2) showing the potential of using the HFI features in discriminating different cognitive load when suitable classifier and features are adopted.
Article Preview

Introduction

Cognitive load refers to the amount of mental effort required to process a given amount of information and has been associated with the limited capacity of working memory (Jimison et al., 2004; Plass, Moreno, & Brünken, 2010). The last decade has witnessed an unprecedented growth in interaction system complexity. Some studies (e.g. Arciszewski, de Greef, & van Delft, 2009; de Greef et al., 2009; Ang, Zaphiris, & Mahmood, 2007) have suggested that, for some complex systems such as air traffic control, crisis management and massively multiplayer role playing games, there may be a competition for the user’s attention and this may tend to lead to cognitive overload, since users often need to simultaneously interact with many different information items on the screen. For example, whilst playing massively multiplayer role playing games, players tend to experience cognitive overload because they must learn to deal with the social dynamics around the game in addition to having to interact with the virtual space and game objects (Ang, Zaphiris, & Mahmood, 2007). On the other hand, Endsley and Kiris (1995) also reported that cognitive underload may lead to performance degradations because users might get out of the information processing loop as they became a passive monitor.

Adaptive systems have been proposed as one of effective solutions to keeping users within a band of proper cognitive load when interacting these systems (e.g. De Greef, Arciszewski, & Neerincx, 2010; Rouse, 1988; Wilson & Russell, 2003; Parasuraman, Mouloua, & Molloy, 1996). The nature of adaption is to provide the best match between task demands and cognitive resources of users. Studies showed that adaptive systems could enhance performance (Hollands & Wickens, 1999; Wilson & Russell, 2007), reduce workload (Hilburn et al., 1997; Scerbo, 1996), and improve situation awareness (Kaber et al., 2006). However, trigger strategy is still one of the challenging factors in developing successful adaptive systems (de Greef et al., 2009; Rowe, Sibert, & Irwin, 1998), since there still lacks an effective method for understanding and evaluating cognitive load. We have witnessed a growing interest in evaluating and understanding users’ cognitive load in the last decade (e.g. de Greef & Arciszewski, 2007; de Greef et al., 2009; Lin, Imamiya, & Mao, 2008; Neerincx, 2003; Sweeney, Maguire, & Shackel, 1993; Wilson & Angela Sasse, 2004). For example, Neerincx (2003) presented a cognitive task load (CTL) model with the aim of exploring cognitive load factors. The CTL model is comprised of three load factors: percentage time occupied, the level of information processing, and task-set switching, which constitute a three-dimensional space in which all user activities can be projected as a combined factor. Recent studies also highlighted the necessity of managing and evaluating cognitive load in educational game environments (e.g. Kalyuga & Plass, 2009), explored different types of cognitive overload in MMORPGs and presented strategies to overcome them (Ang et al., 2007). Some traditional methods have been adopted, with some success for evaluating cognitive load (Kramer, 1991; Paas, et al., 2003), including physiological, subjective (self-report) (e.g. Paas & Van Merriënboer, 1994a) and performance measures (e.g. Jameson et al., 2009). The three measures have their own advantages and disadvantages (see section 2 for details) and the current challenge in cognitive load evaluation mainly lies in how to develop a method which can not only unobtrusively gather data without supplement equipment but also objectively, quantitatively and in real-time evaluate cognitive load based the data. Also, the method should be suitable for deployment in real-life scenarios.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 14: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing