中文摘要：

针对电子商务推荐系统中,互联网＂信息过载＂所造成的难以精确定位用户兴趣并提供准确产品推荐的问题,通过深入挖掘电子商务社区中丰富的用户评论信息,开发产品特征提取算法,建立用户兴趣偏好模型,结合用户历史评分数据来改善传统协同过滤推荐算法的推荐准确性;利用相似度传递技术在一定程度上缓解推荐系统中数据稀疏性带来的问题.实验结果表明,在数据稀疏的情况下,该算法仍可较好地拟合用户对产品的兴趣偏好,并在推荐准确性方面较传统的协同过滤算法有明显的提高.

英文摘要：

In E-commerce recommendation system,＂Information overload＂ on Internet has brought a tough problem,which is how to precisely position users＇ interest and provide users with accurate product recommendation.To solve this problem,in this paper,a product characteristic extraction algorithm was developed and a user preference model was constructed by deeply mining large-scale of user reviews in E-commerce community,to improve accuracy of traditional collaborative filtering recommendation algorithm with coordination of historic user rating information;moreover,data sparsity problem was alleviated with similarity propagation technique.Experiment results show that,in condition of sparse data,algorithm in this paper can still fit product preference of users very well,and has significantly improvement in accuracy compared with traditional collaborative filtering algorithm.