A Neural Architecture for Detecting Confusion in Eye-tracking Data

TL;DR

This paper presents a neural network architecture combining RNN and CNN components to detect user confusion from eye-tracking data, demonstrating significant performance improvements over traditional models.

Contribution

The study introduces a novel neural architecture that leverages both temporal and visuospatial features for confusion detection in eye-tracking data.

Findings

22% improvement in sensitivity and specificity over previous models

Effective use of combined RNN and CNN for eye-tracking analysis

Demonstrated applicability in user interaction scenarios

Abstract

Encouraged by the success of deep learning in a variety of domains, we investigate a novel application of its methods on the effectiveness of detecting user confusion in eye-tracking data. We introduce an architecture that uses RNN and CNN sub-models in parallel to take advantage of the temporal and visuospatial aspects of our data. Experiments with a dataset of user interactions with the ValueChart visualization tool show that our model outperforms an existing model based on Random Forests resulting in a 22% improvement in combined sensitivity & specificity.