Decision Prediction Using Visual Patterns

摘要: Lack of understanding users' underlying decision making process results in the bottleneck EB-HCI eye movement-based human-computer interaction systems. Meanwhile, considerable findings on visual features have been derived from cognitive researches over past few years. A promising method prediction systems is presented this article, which inspired by looking behavior when a user makes decision. As two making, gaze bias and pupil dilation are considered into judging intensions. This combines history movements to given interface traits users. Hence, it improves performance more natural objective way. We apply an either-or choice task commercial Web pages test its effectiveness. Although result shows good only but not predict decision, proves that hiring users effective approach improve automatic triggering