Gaze cluster analysis reveals heterogeneity in attention allocation and predicts learning outcomes

TL;DR

A new gaze analysis method identifies different attention patterns in viewers of instructional videos and predicts learning outcomes.

Contribution

Introduces gaze cluster membership (GCM) as a novel gaze measure to detect multiple attention foci in learners.

Findings

DBSCAN clustering of gaze data identifies meaningful attention patterns in instructional video viewers.

Low inter-subject correlation (ISC) values do not always indicate inattention during multiple meaningful foci.

GCM predicts self-reported mental effort and knowledge retention in learners.

Abstract

Instructional videos need to maintain learners’ attention to foster learning, therefore, a fine-grained measurement of attention is required. Existing gaze measures like inter-subject correlation (ISC) assume a singular focal point deemed meaningful for indicating attention. We argue that multiple meaningful foci can exist and propose an automatically generated gaze measure labeled gaze cluster membership (GCM). By applying the density-based clustering in spatial databases (DBSCAN) algorithm to gaze position data from over 100 participants, we categorize viewers as attentive when they are part of a cluster and as inattentive when they are not. Using two videos, we demonstrate that our settings of DBSCAN generate meaningful clusters. We show that low ISC values (neuronal and eye tracking data) during multiple meaningful foci do not necessarily indicate a lack of attention. Additionally, GCM predicts participants’ self-reported mental effort and their tested knowledge. Our innovative approach is of high value for assessing learner attention and designing instructional videos.

Figures