摘要：

在意见挖掘中，为实现特殊领域知识的语义相关度计算，提出基于Wikipedia的语义相关度计算方法。在构建Wikipedia类别树的基础上，通过Wikipedia类别向量表示Wikipedia中的词汇，形成一部包含各种领域知识的Wikipedia词典，利用该词典计算语义相关度。实验结果表明，该方法的斯皮尔曼等级相关系数可达到0.77。

关键词: 语义相关度, 领域知识, Wikipedia类别树, 意见挖掘

Abstract:

n order to compute semantic relevancy for the specific domain knowledge in opinion mining, this paper proposes a semantic relevancy computing method based on Wikipedia. On the basis of constructing a category tree from Wikipedia, it represents the vast words in Wikipedia by using the category and the result in a Wikipedia dictionary which contains rich domain-specific knowledge, and then computes semantic relevancy by using the dictionary. Experimental results show Spearman rank correlation coefficient of this method can reach 0.77.

Key words: semantic relevancy, domain knowledge, Wikipedia category tree, opinion mining

中图分类号: 

• TP391.43