Classification of Eye Tracking Data Using a Convolutional Neural Network

Abstract

Historically, eye tracking analysis has been a useful approach to identify areas of interest (AOIs) where users have specific regions of the user interface (UI) in which they are interested. Many algorithms have been proposed to analyze eye tracking data in order to make user interfaces more effective. The objective of this study is to use convolutional neural networks (CNNs) to classify eye tracking data. First, a CNN was used to classify two different web interfaces for browsing news data. Then in a second experiment, a CNN was used to classify the nationalities of users. In addition, techniques of data-preprocessing and feature-engineering were applied. The algorithm used in this research is convolutional neural network (CNN), which is famous in deep learning field. Keras framework running on top of TensorFlow was used to define and train our CNN model. The purpose of this research is to explore how feature-engineering can affect evaluation metrics about our model. The results of the study show a number of interesting patterns and generally that deep learning shows promise in the analysis of eye tracking data.