.png){kind=icon}
.png){kind=icon}
Return
Detecting task demand via an eye tracking machine learning system
.png){kind=icon}
PRE
AI
DOI：10.1016/j.dss.2018.10.012.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Computerized systems play a significant role in today's fast-paced digital economy. Because task demand is a major factor that influences how computerized systems are used to make decisions, identifying task demand automatically provides an opportunity for designing advanced decision support systems that can respond to user needs at a personalized level. A first step for designing such advanced decision tools is to investigate possibilities for developing automatic task load detectors. Grounded in decision making, eye tracking, and machine learning literature, we argue that task demand can be detected automatically, reliably, and unobtrusively using eye movements only. To investigate this possibility, we developed an eye tracking task load detection system and tested its effectiveness. Our results revealed that our task load detection system reliably predicted increased task demand from users' eye movement data. These results and their implications for research and practice are discussed.
Keywords:
Human computer interaction
Eye tracking
Task demand
Adaptive decision making
Cognitive effort
Machine learning
Journal
IF:
6.8
Papers:
3.8K
Citations:
1.5W