欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对现有网页信息抽取方法普遍存在人工耗时大、抽取准确率低等问题，提出了一种基于加权频繁子树相似度的网页评论信息抽取方法WTS。首先通过视觉特征对网页进行剪枝处理；然后，通过深度加权的相似度度量方法抽取最佳频繁子树；最后，通过子树对齐方法抽取评论路径并解析评论内容。通过对京东、苏宁等网站的评论内容抽取实验，验证了WTS方法比D—EEM、POL等方法在抽取产品评论信息上具有一定的优势。
英文摘要：
Aiming at the problem that existing methods are time consuming and poor performance, this paper proposed WTS method based on weighted frequent sub-tree similarity, which could extract product comments information rapidly and accurately. Firstly, the method pruned Web pages through visual characteristics. Then, extracted the best frequent sub-tree by depthweighted similarity measure. Lastly, it extracted comment path and parsed comment content. Extracting product comments from the wcbsite of JD, SN and so on, experimental results show that WTS has better performance in extracting product comments than D-EEM and POL.
同期刊论文项目
同项目期刊论文
期刊信息
位置：