Processing Data Visualizations with Seductive Details Using AI-Enabled Analysis of Eye Movement Saliency Maps

Understanding how learners process data visualizations with seductive details is essential for improving comprehension and engagement. This study examined the influence of task-relevant and task-irrelevant seductive details on attentional distribution and comprehension in the context of data story learning, using COVID-19 data visualizations as experimental materials. A gaze-based methodology was applied, using eye-movement data and saliency maps to visualize learners’ attentional patterns while processing bar graphs with varying embellishments. Results showed that task-relevant seductive details supported comprehension for learners with higher visuospatial abilities by guiding attention toward textual information, while task-irrelevant details hindered comprehension, particularly for those with lower visuospatial abilities who focused disproportionately on visual elements. Working memory capacity emerged as a significant predictor of attentional distribution. Additionally, repeated exposure to data visualizations enhanced participants’ ability to recognize visualization types, improving efficiency and reducing reliance on legends and supplementary text. Overall, this study highlights the cognitive mechanisms underlying visualization processing in data story learning and provides practical implications for education, human–computer interaction, and adaptive technology design, emphasizing the importance of tailoring visualization strategies to individual learner differences.