一种基于眼动的网购商品推荐方法

An Approach to Online Commodity Recommendation Based on Eye Movements

为了解决电子商务推荐系统的"冷启动"问题,帮助消费者快速有效地找到所需商品,提出一种基于眼动的网购商品推荐方法。首先,该方法将眼动作为一种隐式评分信息,用来说明消费者意图需求的高层语义;其次,提取商品图像的底层视觉特征,用于描述商品的特征属性;最后,使用排序支持向量机算法搭建商品特征属性与消费者意图需求之间的语义"桥梁"。实验结果表明,该推荐方法能够对原始的推荐结果进行重排序,有效地将消费者所需商品排在推荐结果的前列。

To solve the cold-start problem of E-Commerce Recommender System, this paper proposes an approach to online commodity recommendation based on eye movements to help consumers quickly and effectively find what they want during online shopping. This paper begins with taking eye movements as a kind of implicit rating information to explain high-level semantic concept of consumers＇ needs. Next, our proposed approach extracts low-level visual features of commodity images to describe their feature attribute. Finally, we use ranking support vector machine algorithm to bridge the gap between the feature attribute of merchandises and consumers＇ needs. The results of experiments indicate that the proposed method can reorder the original recommendation results, and merchandises preferred by consumers are the top few ones of the recommendation results.