论文部分内容阅读
随着新浪等微博用户的不断增长,微博网站已经成为人们获取信息和创造信息的主要平台。现有微博平台的检索功能只能靠关键词匹配返回检索结果,使得检索结果无法满足用户需求。为了解决该问题,提出一种基于HowNet知识库系统的微博语义检索方法。利用HowNet知识库系统分别将中文待检索主题词和微博文本词汇进行语义相关度匹配,返回和待检索词汇语义相关度较高的微博文本,最后针对新浪微博数据集进行语义检索实验。实验结果表明,利用HowNet系统能够从语义层面上获得较高的查准率,为用户提供更满意的检索效果。
As the number of Weibo users such as Sina continues to grow, Weibo websites have become the main platform for people to access information and create information. The retrieval function of the existing Weibo platform can only return the retrieval result by keyword matching, which makes the retrieval result unable to meet the user’s needs. In order to solve this problem, this paper proposes a Weibo semantic retrieval method based on HowNet knowledge base system. We use the HowNet knowledge base system to respectively match the semantic relevancy between Chinese keywords to be searched and the texts of Weibo texts, and return the weibo texts that have a high correlation with the semantic meaning of the words to be searched. Finally, the semantic retrieval experiment is carried out on the Sina Weibo data sets. The experimental results show that the use of HowNet system can get a higher level of accuracy from the semantic level, to provide users with more satisfactory search results.