Visualization and Comparison of AOI Transitions with Force-Directed Graph Layout

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.