2025/05/24 by Yuri Miyagi, Nils Rodrigues, Miyagi, Yuri +5
Computer Science · #Data Visualization and Analytics #FOS: Computer and information sciences #Graph Theory and Algorithms #Human-Computer Interaction (cs.HC)
paper · pdf · doi:10.48550/arxiv.2506.00028
openalex publication_date 2025/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
By analyzing the gaze trajectories of people viewing screens and advertisements, we can determine what people are interested in. This knowledge can be effective when recommending commercial products and services, and also, when improving advertisement design. Therefore, analysis and visualization of eye gaze have been an active research topic. This paper proposes a new method for visualizing patterns of the gaze trajectories of multiple people by (1) visualizing patterns that move through multiple areas of interest (AOI) and (2) visualizing differences among multiple gaze trajectories. The method first constructs a hierarchical AOI structure to a Web page or an image, and uses this structure to convert the trajectory into a sequence of symbols. We apply N-grams to the generated symbol sequences to extract transition patterns between AOIs. Finally, the method visualizes a list of the pattern extraction results and the shapes of the characteristic elements. We present the visualization of gaze trajectories for three examples of stimuli, and argue that analysts can efficiently discover trends in gaze transitions between text and figures, as well as differences between participants of the eye-tracking experiments.