摘要： 随着博客数据的迅速增长，在网络媒体中进行信息检索时的效率问题日益受到人们的关注。该文在针对博客搜索中特有的用户需求以及博客系统自身特点进行分析的基础上，提出一种基于博客文章相关性、时效性、查询类型和博客作者兴趣特征一致性等多特征融合的博客文章排序算法。实验结果证明了该算法性能优于传统算法。

关键词: 博客, 信息检索, 排序, 多特征融合, 兴趣特征

Abstract: With the rapid development of Blog data, the efficiency of information retrieval in them is of great concern. Based on the analysis of the peculiar users’ needs and the special feature of Blog system, this paper proposes a new sorting algorithm on the basis of the integration of multi features like relativity, timeliness, query type, Blog writer’s interest characteristics and so on. Experimental result proves that the performance of the new algorithm is more efficient than the traditional ones.

Key words: Blog, information retrieval, sorting, fusion of multi features, interest characteristics

中图分类号: 

• TP391