2025/08/06 by Yuting, Zhu, Xinyu, Cao, Yuzhuo, Su +1
#FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)
paper · doi:10.48550/arxiv.2508.04541
A common challenge for e-commerce sellers is to decide what product images to display on online shopping sites. In this paper, we propose and validate a novel metric, k-value, to quantify the information richness of an image set, and we further investigate its effect on consumers' purchase decisions. We leverage patch-level embeddings from Vision Transformers (ViT) and apply k-means clustering to identify distinct visual features, defining k-value as the number of clusters. An online experiment demonstrates that k-value aligns with human-perceived information richness, validating the metric. A simulated online shopping experiment further reveals a significant yet counterintuitive result: while an image set with a higher k-value (richer information) shortens decision time, it paradoxically reduces purchase propensity. Our findings illuminate the complex relationship between visual information richness and consumer behavior, providing sellers a quantifiable tool for image selection.