Cross-subject workload classification using pupil-related measures

Appel, Tobias; Scharinger, Christian; Gerjets, Peter; Kasneci, Enkelejda

doi:10.1145/3204493.3204531

Cited by 46 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiment was conducted using arithmetical tasks defining seven levels of cognitive workload, where the first level was the easiest and contained one and two-digit numbers, and the seventh level was related to arithmetical tasks on three-digit numbers with three carries. The authors attempted to classify the three and two cognitive workload levels using a subject-independent and dependent approach based on the pupil data from 25 participants [ 42 ]. In [ 43 ], two approaches were applied to create a classification model as well.…”

Section: Related Workmentioning

confidence: 99%

Interpretable Machine Learning Models for Three-Way Classification of Cognitive Workload Levels for Eye-Tracking Features

2021

View full text Add to dashboard Cite

The paper is focussed on the assessment of cognitive workload level using selected machine learning models. In the study, eye-tracking data were gathered from 29 healthy volunteers during examination with three versions of the computerised version of the digit symbol substitution test (DSST). Understanding cognitive workload is of great importance in analysing human mental fatigue and the performance of intellectual tasks. It is also essential in the context of explanation of the brain cognitive process. Eight three-class classification machine learning models were constructed and analysed. Furthermore, the technique of interpretable machine learning model was applied to obtain the measures of feature importance and its contribution to the brain cognitive functions. The measures allowed improving the quality of classification, simultaneously lowering the number of applied features to six or eight, depending on the model. Moreover, the applied method of explainable machine learning provided valuable insights into understanding the process accompanying various levels of cognitive workload. The main classification performance metrics, such as F1, recall, precision, accuracy, and the area under the Receiver operating characteristic curve (ROC AUC) were used in order to assess the quality of classification quantitatively. The best result obtained on the complete feature set was as high as 0.95 (F1); however, feature importance interpretation allowed increasing the result up to 0.97 with only seven of 20 features applied.

show abstract

Section: Related Workmentioning

confidence: 99%

Interpretable Machine Learning Models for Three-Way Classification of Cognitive Workload Levels for Eye-Tracking Features

2021

View full text Add to dashboard Cite

show abstract

“…Pupil diameter has been used to assess cognitive load [14] . Task difficulty [15] , emotional arousal [16] , fatigue [17] , and pain [18] have also been studied using pupil diameter measurements. However, pupil dilations can occur due to different illumination conditions.…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

FakeNewsPerception: An eye movement dataset on the perceived believability of news stories

et al. 2021

Self Cite

View full text Add to dashboard Cite

Extensive use of the internet has enabled easy access to many different sources, such as news and social media. Content shared on the internet cannot be fully fact-checked and, as a result, misinformation can spread in a fast and easy way. Recently, psychologists and economists have shown in many experiments that prior beliefs, knowledge, and the willingness to think deliberately are important determinants to explain who falls for fake news. Many of these studies only rely on self-reports, which suffer from social desirability. We need more objective measures of information processing, such as eye movements, to effectively analyze the reading of news. To provide the research community the opportunity to study human behaviors in relation to news truthfulness, we propose the FakeNewsPerception dataset. FakeNewsPerception consists of eye movements during reading, perceived believability scores, questionnaires including Cognitive Reflection Test (CRT) and News-Find-Me (NFM) perception, and political orientation, collected from 25 participants with 60 news items. Initial analyses of the eye movements reveal that human perception differs when viewing true and fake news.

show abstract

“…Pupillary information -Since pupil diameter has been used used as an indicator of cognitive load, short-term memory, language processing, reasoning, perception, sustained attention, and selective attention [49][50][51][52][53], we also include the mean pupil diameter in our data analysis (meanPupilDiameter) and explicitly investigate its relationship to fluid intelligence.…”

Section: The Tüeyeq Data Setmentioning

confidence: 99%

Do your eye movements reveal your performance on an IQ test? A study linking eye movements and socio-demographic information to fluid intelligence.

Kasneci¹,

Kasneci²,

Trautwein³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Understanding the main factors contributing to individual differences in fluid intelligence is one of the main challenges of psychology. A vast body of research and numerous empirical findings are based on the framework of the Cultural-Fair IQ test 20-R (CFT 20-R). In this work, we extend and complement the current state of research by analysing the relationship of socio-demographic and eye-movement-related information and the ability of a participant to correctly solve a CFT test item. Our work shows that a participant's eye movements while solving a CFT test item contain discriminative information and can be used to predict whether the participant will succeed in the current task. Moreover, the information related to eye movements complements the information provided by socio-demographic data when it comes to success prediction. In combination, both types of information yield a significantly higher predictive performance than each information type individually. To better understand the influence of features related to eye movements and socio-demographic information for the prediction of a participant's performance on a CFT item, we employ state-of-the-art explainability techniques and show that, along with socio-demographic variables, eye-movement data, especially the number of saccades and the mean pupil diameter, adds highly discriminating power. This ultimately suggests more efficient processing and more invested mental effort. Beyond the specific contribution to research on the relationship between eye movements and fluid intelligence, the findings presented in this work pave the way for further in-depth investigations of factors predicting fluid intelligence.

show abstract

Cross-subject workload classification using pupil-related measures

Cited by 46 publications

References 24 publications

Interpretable Machine Learning Models for Three-Way Classification of Cognitive Workload Levels for Eye-Tracking Features

Interpretable Machine Learning Models for Three-Way Classification of Cognitive Workload Levels for Eye-Tracking Features

FakeNewsPerception: An eye movement dataset on the perceived believability of news stories

Do your eye movements reveal your performance on an IQ test? A study linking eye movements and socio-demographic information to fluid intelligence.

Contact Info

Product

Resources

About