A Scenario-based Analysis of Front-facing Camera Eye Tracker for UX-UI Survey on Mobile Banking App

Abstract

Recently, User Experience and User Interface (UX-UI) have become important aspects in designing an effective mobile banking application. Traditionally, developers and designers have relied on explicit feedback derived from questionnaires to gain more insights into UX-UI. With the advancement of new technology, eye-tracking device has been introduced, and the approach has been used to provide a digital footprint indicating exact gazing positions of the users when using an application. So far, many studies have acknowledged the benefits of eye movement tracking and exploited such implicit feedback, alongside the result yielded from a survey. Successful uses of this eye-tracking device would further the development of mobile banking application. In this study, we aimed to build a device-free eye tracking software module that would work efficiently on mobile phones. To achieve this goal, we employed an existing Convolutional Neural Network model in our framework and evaluated the model when it was applied to the specific domain, i.e., UX-UI research design for mobile banking apps. We investigated a GazeCapture dataset, the first large-scale dataset for eye tracking, and conducted a data wrangling technique. The results show that fine-tuning the model with our wrangled data can improve the overall eye-tracking performance. Moreover, enabling user calibration can clearly enhance the predicting performance of the model.