A Neural Architecture for Detecting Confusion in Eye-tracking Data
This work addresses the problem of understanding user confusion for visualization tool developers, but it is incremental as it applies existing deep learning methods to a new domain.
The paper tackled detecting user confusion in eye-tracking data using a deep learning architecture, achieving a 22% improvement in combined sensitivity and specificity over a Random Forests model on a dataset from the ValueChart visualization tool.
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.