@inproceedings{5445f36121a04e428181e988879a6ed7,
title = "Predicting the Optimal Time for Interruption using Pupillary Data and Classification",
abstract = "In the current study we present an air traffic control (ATC) task in which we measured pupil dilation to automatically determine high and low workload periods. We manipulated working memory (WM) requirements across three conditions: a no WM condition, a passive WM condition in which information was accumulated, and an active WM condition in which information had to be added to and removed from WM. Results showed that no WM resulted in the least dilation, but that passive WM and active WM did not differ. Next, we used the pupil data to train a range of classifiers to differentiate between high and low workload periods with the ultimate goal to create an online task-independent interruption management system (IMS). The best predicting features were the median and a second-order polynomial fit, going back 12 seconds from the to-be-predicted moment. Using these features, our classifier was able to predict workload at high accuracy (77%). We conclude that pupil dilation can be used to create a reliable IMS.",
keywords = "Interruptions, Machine learning, Multitasking, Pupil dilation, Working memory",
author = "Hagit Shaposhnik and Borst, {Jelmer P.} and Taatgen, {Niels A.}",
note = "Publisher Copyright: {\textcopyright} 2018 Proceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018. All rights reserved.; 40th Annual Meeting of the Cognitive Science Society: Changing Minds, CogSci 2018 ; Conference date: 25-07-2018 Through 28-07-2018",
year = "2018",
month = jan,
day = "1",
language = "English",
series = "Proceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018",
publisher = "The Cognitive Science Society",
pages = "2479--2484",
booktitle = "Proceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018",
}