Combining Automation and Expertise: A Semi-automated Approach to Correcting Eye Tracking Data in Reading Tasks

TL;DR

Drift in eye-tracking data during reading can misplace fixations, compromising word- and line-level analyses. The authors present Fix8, an open-source GUI that enables semi-automated correction by coupling automated suggestions with user validation. In a within-subject usability study (N=14), Fix8 achieved a 44% reduction in correction time without sacrificing accuracy, and users reported lower workload and higher perceived performance. Beyond correction, Fix8 offers synthetic data generation, visualization, AOI analyses, and data format converters, illustrating a practical, open-source eye-tracking toolbox for reading research.

Abstract

In reading tasks drift can move fixations from one word to another or even another line, invalidating the eye tracking recording. Manual correction is time-consuming and subjective, while automated correction is fast yet limited in accuracy. In this paper we present Fix8 (Fixate), an open-source GUI tool that offers a novel semi-automated correction approach for eye tracking data in reading tasks. The proposed approach allows the user to collaborate with an algorithm to produce accurate corrections faster without sacrificing accuracy. Through a usability study (N=14) we assess the time benefits of the proposed technique, and measure the correction accuracy in comparison to manual correction. In addition, we assess subjective workload through NASA Task Load Index, and user opinions through Likert-scale questions. Our results show that on average the proposed technique was 44% faster than manual correction without any sacrifice in accuracy. In addition, users reported a preference for the proposed technique, lower workload, and higher perceived performance compared to manual correction. Fix8 is a valuable tool that offers useful features for generating synthetic eye tracking data, visualization, filters, data converters, and eye movement analysis in addition to the main contribution in data correction.

Figures (16)

• Figure 1: An illustration of drift where fixations deviate from their real position.
• Figure 2: Examples of good and bad suggestions in the assisted correction approach. The magenta circle represents the current fixation being considered, fixations in red are previous fixations, and the blue circle is the suggested correction position.
• Figure 3: Illustrating how user intervention through drag and drop triggers rerunning of the correction algorithm with the updated fixation position information yielding better suggestions. Green circles represent correct fixations, blue circle represents the current suggestion, and grey circles represent future suggestions.
• Figure 4: Visualization Panel.
• Figure 5: Visualization showing remaining fixations in grey.