Using Psychophysiological Sensors to Assess Mental Workload During Web Browsing

Area of Science:

• Human-Computer Interaction
• Cognitive Science
• Biomedical Engineering

Background:

• Assessing user mental workload during web browsing is crucial for optimizing user experience.
• Continuous mental workload assessment presents significant challenges in real-time browsing scenarios.

Purpose of the Study:

• To develop and validate a method for classifying mental workload levels during web browsing.
• To investigate the correlation between physiological responses and mental workload.
• To enhance the accuracy of mental workload assessment by integrating multiple psychophysiological signals.

Main Methods:

• Utilized high-frequency, non-invasive psychophysiological sensors including eye-tracking (pupil dilation), electrodermal activity (EDA), electrocardiogram (ECG), photoplethysmography (PPG), electroencephalogram (EEG), and temperature.
• Developed a classification method combining data from multiple sensors to identify distinct mental workload levels.
• Conducted an experiment to measure physiological responses during a web browsing task.

Main Results:

• Identified four distinct levels of mental workload associated with web browsing tasks.
• Pupil dilation analysis effectively indicated different mental workload levels.
• The combined sensor approach achieved a classification accuracy of 93.7% for mental workload.

Conclusions:

• Integrating multiple psychophysiological signals significantly improves the accuracy of mental workload classification.
• The developed method offers a robust approach for real-time mental workload assessment during web browsing.
• Findings provide valuable insights for designing more user-centric and less demanding web interfaces.