A comparison of four methods for cognitive load measurement

Abstract

Recognizing users' cognitive load during tasks is among the most important considerations for adaptive automation and interface evaluation. This paper compares four methods of measuring user cognitive load, that is, subjective rating of task difficulty, task completion time, performance accuracy and eye activity based physiological measurement. In order to be practically useful, the measurement should be sensitive to task difficulty variation and accurately predict user cognitive load. In this study, we examined the sensitivity and accuracy of these measures for five levels of cognitive load. ANOVA tests and Gaussian mixture model classification results show that subjective rating of task difficulty is the most effective measure, meanwhile eye activity based measure is as sensitive and accurate as using task completion time to classify two or more cognitive load levels, but has the relative advantage of being a real time measure and not requiring a specific action.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 63 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.